3.1.1 Research axis 1

Our first objective is to stay at a state-of-the-art level in key NLP tasks such as shallow processing, part-of-speech tagging and (syntactic) parsing, which are core expertise domains of ALMAnaCH members. This will also require us to improve the generation of semantic representations (semantic parsing), and to begin to explore tasks such as machine translation, which now relies on neural architectures also used for some of the above-mentioned tasks. Given the generalisation of neural models in NLP, we will also be involved in better understanding how such models work and what they learn, something that is directly related to the investigation of language variation (Research axis 2). We will also work on the integration of both linguistic and non-linguistic contextual information to improve automatic linguistic analysis. This is an emerging and promising line of research in NLP. We will have to identify, model and take advantage of each type of contextual information available. Addressing these issues will enable the development of new lines of research related to conversational content. Applications include improved information and knowledge extraction algorithms. We will especially focus on challenging datasets such as domain-specific texts (e.g. financial, legal) as well as historical documents, in the larger context of the development of digital humanities. We currently also explore the even more challenging new direction of a cognitively inspired NLP, in order to tackle the possibility to enrich the architecture of state-of-the-art algorithms, such as RNNGs, based on human neuroimaging-driven data.

3.1.2 Research axis 2

Language variation must be better understood and modelled in all its forms. In this regard, we will put a strong emphasis on four types of language variation and their mutual interaction: sociolinguistic variation in synchrony (including non-canonical spelling and syntax in user-generated content), complexity-based variation in relation to language-related disabilities, and diachronic variation (computational exploration of language change and language history, with a focus on Old to all forms of Modern French, as well as Indo-European languages in general). In addition, the noise introduced by Optical Character Recognition and Handwritten Text Recognition systems, especially in the context of historical documents, bears some similarities to that of non-canonical input in user-generated content (e.g. erroneous characters). This noise constitutes a more transverse kind of variation stemming from the way language is graphically encoded, which we call language-encoding variation. Other types of language variation will also become important research topics for ALMAnaCH in the future. This includes dialectal variation (e.g. work on Arabic varieties, something on which we have already started working, producing the first annotated data set on Maghrebi Arabizi, the Arabic variants used on social media by people from North-African countries, written using a non-fixed Latin-script transcription) as well as the study and exploitation of paraphrases in a broader context than the above-mentioned complexity-based variation.

Both research axes above rely on the availability of language resources (corpora, lexicons), which is the focus of our third, transverse research axis.

3.1.3 Research axis 3

Language resource development (raw and annotated corpora, lexical resources) is not just a necessary preliminary step to create both evaluation datasets for NLP systems and training datasets for NLP systems based on machine learning. When dealing with datasets of interest to researchers from the humanities (e.g. large archives), it is also a goal per se and a preliminary step before making such datasets available and exploitable online. It involves a number of scientific challenges, among which (i) tackling issues related to the digitalisation of non-electronic datasets, (ii) tackling issues related to the fact that many DH-related datasets are domain-specific and/or not written in contemporary languages; (iii) the development of semi-automatic and automatic algorithms to speed up the work (e.g. automatic extraction of lexical information, low-resource learning for the development of pre-annotation algorithms, transfer methods to leverage existing tools and/or resources for other languages, etc.) and (iv) the development of formal models to represent linguistic information in the best possible way, thus requiring expertise at least in NLP and in typological and formal linguistics. Such endeavours are domains of expertise of the ALMAnaCH team, and a large part of our research activities will be dedicated to language resource development. In this regard, we aim to retain our leading role in the representation and management of lexical resource and treebank development and also to develop a complete processing line for the transcription, analysis and processing of complex documents of interest to the humanities, in particular archival documents. This research axis 3 will benefit the whole team and beyond, and will benefit from and feed the work of the other research axes.

3.2.1 Processing of natural language at all levels: morphology, syntax, semantics

Our expertise in NLP is the outcome of more than 10 years in developing new models of analysis and accurate techniques for the full processing of any kind of language input since the early days of the Atoll project-team and the rise of linguistically informed data-driven models as put forward within the Alpage project-team.

Traditionally, a full natural language process (NLP) chain is organised as a pipeline where each stage of analysis represents a traditional linguistic field (in a structuralism view) from morphological analysis to purely semantic representations. The problem is that this architecture is vulnerable to error propagation and very domain sensitive: each of these stage must be compatible at the lexical and structure levels they provide. We arguably built the best performing NLP chain for French 70, 114 and one of the best for robust multilingual parsing as shown by our results in various shared tasks over the years 110, 107, 115, 76. So we pursue our efforts on each of our components we developed: tokenisers (e.g. SxPipe), part-of-speech taggers (e.g. MElt), constituency parsers and dependency parsers (e.g. FRMG, DyALog-SR) as well as our recent neural semantic graph parsers 107.

In particular, we continue to explore the hybridisation of symbolic and statistical approaches, and extend it to neural approaches, as initiated in the context of our participation to the CoNLL 2017 multilingual parsing shared task 2 and to Extrinsic Parsing Evaluation Shared Task 3.

Fundamentally, we want to build tools that are less sensitive to variation, more easily configurable, and self-adapting. Our short-term goal is to explore techniques such as multi-task learning (cf. already  99) to propose a joint model of tokenisation, normalisation, morphological analysis and syntactic analysis. We also explore adversarial learning, considering the drastic variation we face in parsing user-generated content and processing historical texts, both seen as noisy input that needs to be handled at training and decoding time.

3.2.2 Integrating context in NLP systems

While those points are fundamental, therefore necessary, if we want to build the next generation of NLP tools, we need to push the envelop even further by tackling the biggest current challenge in NLP: handling the context within which a speech act is taking place.

There is indeed a strong tendency in NLP to assume that each sentence is independent from its siblings sentences as well as its context of enunciation, with the obvious objective to simplify models and reduce the complexity of predictions. While this practice is already questionable when processing full-length edited documents, it becomes clearly problematic when dealing with short sentences that are noisy, full of ellipses and external references, as commonly found in User-Generated Content (UGC).

A more expressive and context-aware structural representation of a linguistic production is required to accurately model UGC. Let us consider for instance the case for Syntax-based Machine Translation of social media content, as is carried out by the ALMAnaCH-led ANR project Parsiti (PI: DS). A Facebook post may be part of a discussion thread, which may include links to external content. Such information is required for a complete representation of the post's context, and in turn its accurate machine translation. Even for the presumably simpler task of POS tagging of dialogue sequences, the addition of context-based features (namely information about the speaker and dialogue moves) was beneficial 79. In the case of UGC, working across sentence boundaries was explored for instance, with limited success, by 69 for document-wise parsing and by 98 for POS tagging.

Taking the context into account requires new inference methods able to share information between sentences as well as new learning methods capable of finding out which information is to be made available, and where. Integrating contextual information at all steps of an NLP pipeline is among the main research questions addressed in this research strand. In the short term, we focus on morphological and syntactic disambiguation within close-world scenarios, as found in video games and domain-specific UGC. In the long term, we investigate the integration of linguistically motivated semantic information into joint learning models.

From a more general perspective, contexts may take many forms and require imagination to discern them, get useful data sets, and find ways to exploit them. A context may be a question associated with an answer, a rating associated with a comment (as provided by many web services), a thread of discussions (e-mails, social media, digital assistants, chatbots—on which see below–), but also meta data about some situation (such as discussions between gamers in relation with the state of the game) or multiple points of views (pictures and captions, movies and subtitles). Even if the relationship between a language production and its context is imprecise and indirect, it is still a valuable source of information, notwithstanding the need for less supervised machine learning techniques (cf. the use of LSTM neural networks by Google to automatically suggest replies to emails).

3.2.3 Information and knowledge extraction

The use of local contexts as discussed above is a new and promising approach. However, a more traditional notion of global context or world knowledge remains an open question and still raises difficult issues. Indeed, many aspects of language such as ambiguities and ellipsis can only be handled using world knowledge. Linked Open Data (LODs) such as DBpedia, WordNet, BabelNet, or Framebase provide such knowledge and we plan to exploit them.

However, each specialised domain (economy, law, medicine...) exhibits its own set of concepts with associated terms. This is also true of communities (e.g. on social media), and it is even possible to find communities discussing the same topics (e.g. immigration) with very distinct vocabularies. Global LODs weakly related to language may be too general and not sufficient for a specific language variant. Following and extending previous work in ALPAGE, we put an emphasis on information acquisition from corpora, including error mining techniques in parsed corpora (to detect specific usages of a word that are missing in existing resources), terminology extraction, and word clustering.

Word clustering is of specific importance. It relies on the distributional hypothesis initially formulated by Harris, which states that words occurring in similar contexts tend to be semantically close. The latest developments of these ideas (with word2vec or GloVe) have led to the embedding of words (through vectors) in low-dimensional semantic spaces. In particular, words that are typical of several communities (see above) can be embedded in a same semantic space in order to establish mappings between them. It is also possible in such spaces to study static configurations and vector shifts with respect to variables such as time, using topological theories (such as pretopology), for instance to explore shifts in meaning over time (cf. the ANR project Profiterole concerning ancient French texts) or between communities (cf. the ANR project SoSweet). It is also worth mentioning on-going work (in computational semantics) whose goal is to combine word embeddings to embed expressions, sentences, paragraphs or even documents into semantic spaces, e.g. to explore the similarity of documents at various time periods.

Besides general knowledge about a domain, it is important to detect and keep trace of more specific pieces of information when processing a document and maintaining a context, especially about (recurring) Named Entities (persons, organisations, locations...) —something that is the focus of future work in collaboration with Patrice Lopez on named entity detection in scientific texts. Through the co-supervision of a PhD funded by the LabEx EFL (see below), we are also involved in pronominal coreference resolution (finding the referent of pronouns). Finally, we plan to continue working on deeper syntactic representations (as initiated with the Deep Sequoia Treebank), thus paving the way towards deeper semantic representations. Such information is instrumental when looking for more precise and complete information about who does what, to whom, when and where in a document. These lines of research are motivated by the need to extract useful contextual information, but it is also worth noting their strong potential in industrial applications.

3.3.1 Theoretical and empirical synchronic linguistics

Permanent members involved: all

We aim to explore computational models to deal with language variation. It is important to get more insights about language in general and about the way humans apprehend it. We will do so in at least two directions, associating computational linguistics with formal and descriptive linguistics on the one hand (especially at the morphological level) and with cognitive linguistics on the other hand (especially at the syntactic level).

Recent advances in morphology rely on quantitative and computational approaches and, sometimes, on collaboration with descriptive linguists—see for instance the special issue of the Morphology journal on “computational methods for descriptive and theoretical morphology”, edited and introduced by 67. In this regard, ALMAnaCH members have taken part in the design of quantitative approaches to defining and measuring morphological complexity and to assess the internal structure of morphological systems (inflection classes, predictability of inflected forms...). Such studies provide valuable insights on these prominent questions in theoretical morphology. They also improve the linguistic relevance and the development speed of NLP-oriented lexicons, as also demonstrated by ALMAnaCH members. We shall therefore pursue these investigations, and orientate them towards their use in diachronic models (see section 3.3.3).

Regarding cognitive linguistics, we have the perfect opportunity with the starting ANR-NSF project “Neuro-Computational Models of Natural Language” (NCM-NL) to go in this direction, by examining potential correlations between medical imagery applied on patients listening to a reading of “Le Petit Prince” and computation models applied on the novel. A secondary prospective benefit from the project will be information about processing evolution (by the patients) along the novel, possibly due to the use of contextual information by humans.

3.3.2 Sociolinguistic variation

Because language is central in our social interactions, it is legitimate to ask how the rise of digital content and its tight integration in our daily life has become a factor acting on language. This is even more actual as the recent rise of novel digital services opens new areas of expression, which support new linguistic behaviours. In particular, social media such as Twitter provide channels of communication through which speakers/writers use their language in ways that differ from standard written and oral forms. The result is the emergence of new language varieties.

A very similar situation exists with regard to historical texts, especially documentary texts or graffiti but even literary texts, that do not follow standardised orthography, morphology or syntax.

However, NLP tools are designed for standard forms of language and exhibit a drastic loss of accuracy when applied to social media varieties or non-standardised historical sources. To define appropriate tools, descriptions of these varieties are needed. However, to validate such descriptions, tools are also needed. We address this chicken-and-egg problem in an interdisciplinary fashion, by working both on linguistic descriptions and on the development of NLP tools. Recently, socio-demographic variables have been shown to bear a strong impact on NLP processing tools (see for instance 74 and references therein). This is why, in a first step, jointly with researchers involved in the ANR project SoSweet (ENS Lyon and Inria project-team Dante), we will study how these variables can be factored out by our models and, in a second step, how they can be accurately predicted from sources lacking these kinds of featured descriptions.

3.3.3 Diachronic variation

Language change is a type of variation pertaining to the diachronic axis. Yet any language change, whatever its nature (phonetic, syntactic...), results from a particular case of synchronic variation (competing phonetic realisations, competing syntactic constructions...). The articulation of diachronic and synchronic variation is influenced to a large extent by both language-internal factors (i.e. generalisation of context-specific facts) and/or external factors (determined by social class, register, domain, and other types of variation).

Very few computational models of language change have been developed. Simple deterministic finite-state-based phonetic evolution models have been used in different contexts. The PIElexicon project 93 uses such models to automatically generate forms attested in (classical) Indo-European languages but is based on an idiosyncratic and unacceptable reconstruction of the Proto-Indo-European language. Probabilistic finite-state models have also been used for automatic cognate detection and proto-form reconstruction, for example by 68 and 75. Such models rely on a good understanding of the phonetic evolution of the languages at hand.

In ALMAnaCH, our goal is to work on modelling phonetic, morphological and lexical diachronic evolution, with an emphasis on computational etymological research and on the computational modelling of the evolution of morphological systems (morphological grammar and morphological lexicon). These efforts will be in direct interaction with sub-strand 3b (development of lexical resources). We want to go beyond the above-mentioned purely phonetic models of language and lexicon evolution, as they fail to take into account a number of crucial dimensions, among which: (1) spelling, spelling variation and the relationship between spelling and phonetics; (2) synchronic variation (geographical, genre-related, etc.); (3) morphology, especially through intra-paradigmatic and inter-paradigmatic analogical levelling phenomena, (4) lexical creation, including via affixal derivation, back-formation processes and borrowings.

We apply our models to two main tasks. The first task, as developed for example in the context of the ANR project Profiterole, consists in predicting non-attested or non-documented words at a certain date based on attestations of older or newer stages of the same word (e.g., predicting a non-documented Middle French word based on its Vulgar Latin and Old French predecessors and its Modern French successor). Morphological models and lexical diachronic evolution models will provide independent ways to perform the same predictions, thus reinforcing our hypotheses or pointing to new challenges.

The second application task is computational etymology and proto-language reconstruction. Our lexical diachronic evolution models will be paired with semantic resources (wordnets, word embeddings, and other corpus-based statistical information). This will allow us to formally validate or suggest etymological or cognate relations between lexical entries from different languages of a same language family, provided they are all inherited. Such an approach could also be adapted to include the automatic detection of borrowings from one language to another (e.g. for studying the non-inherited layers in the Ancient Greek lexicon). In the longer term, we will investigate the feasibility of the automatic (unsupervised) acquisition of phonetic change models, especially when provided with lexical data for numerous languages from the same language family.

These lines of research will rely on etymological data sets and standards for representing etymological information (see Section 3.4.2).

Diachronic evolution also applies to syntax, and in the context of the ANR project Profiterole, we are beginning to explore more or less automatic ways of detecting these evolutions and suggest modifications, relying on fine-grained syntactic descriptions (as provided by meta-grammars), unsupervised sentence clustering (generalising previous works on error mining, cf. 9), and constraint relaxation (in meta-grammar classes). The underlying idea is that a new syntactic construction evolves from a more ancient one by small, iterative modifications, for instance by changing word order, adding or deleting functional words, etc.

3.3.4 Accessibility-related variation

Language variation does not always pertain to the textual input of NLP tools. It can also be characterised by their intended output. This is the perspective from which we investigate the issue of text simplification (for a recent survey, see for instance  111). Text simplification is an important task for improving the accessibility to information, for instance for people suffering from disabilities and for non-native speakers learning a given language 94. To this end, guidelines have been developed to help writing documents that are easier to read and understand, such as the FALC (“Facile À Lire et à Comprendre”) guidelines for French. 4

Fully automated text simplification is not suitable for producing high-quality simplified texts. Besides, the involvement of disabled people in the production of simplified texts plays an important social role. Therefore, following previous works 73, 105, our goal will be to develop tools for the computer-aided simplification of textual documents, especially administrative documents. Many of the FALC guidelines can only be linguistically expressed using complex, syntactic constraints, and the amount of available “parallel” data (aligned raw and simplified documents) is limited. We will therefore investigate hybrid techniques involving rule-based, statistical and neural approaches based on parsing results (for an example of previous parsing-based work, see  66). Lexical simplification, another aspect of text simplification 82, 95, will also be pursued. In this regard, we have already started a collaboration with Facebook's AI Research in Paris, the UNAPEI (the largest French federation of associations defending and supporting people with intellectual disabilities and their families), and the French Secretariat of State in charge of Disabled Persons.

Accessibility can also be related to the various presentation forms of a document. This is the context in which we have initiated the OPALINE project, funded by the Programme d'Investissement d'Avenir - Fonds pour la Société Numérique. The objective is for us to further develop the GROBID text-extraction suite 5 in order to be able to re-publish existing books or dictionaries, available in PDF, in a format that is accessible by visually impaired persons.

3.4.1 Construction, management and automatic annotation of Text Corpora

Corpus creation and management (including automatic annotation) is often a time-consuming and technically challenging task. In many cases, it also raises scientific issues related for instance with linguistic questions (what is the elementary unit in a text?) as well as computer-science challenges (for instance when OCR or HTR are involved). It is therefore necessary to design a work-flow that makes it possible to deal with data collections, even if they are initially available as photos, scans, wikipedia dumps, etc.

These challenges are particularly relevant when dealing with ancient languages or scripts where fonts, OCR techniques, language models may be not extant or of inferior quality, as a result, among others, of the variety of writing systems and the lack of textual data. We will therefore work on improving print OCR for some of these languages, especially by moving towards joint OCR and language models. Of course, contemporary texts can be often gathered in very large volumes, as we already do within the ANR project SoSweet, resulting in different, specific issues.

ALMAnaCH pays a specific attention to the re-usability 6 of all resources produced and maintained within its various projects and research activities. To this end, we will ensure maximum compatibility with available international standards for representing textual sources and their annotations. More precisely we will take the TEI (Text Encoding Initiative) guidelines as well the standards produced by ISO committee TC 37/SC 4 as essential points of reference.

From our ongoing projects in the field of Digital Humanities and emerging initiatives in this field, we observe a real need for complete but easy work-flows for exploiting corpora, starting from a set of raw documents and reaching the level where one can browse the main concepts and entities, explore their relationship, extract specific pieces of information, always with the ability to return to (fragments of) the original documents. The pieces of information extracted from the corpora also need to be represented as knowledge databases (for instance as RDF “linked data”), published and linked with other existing databases (for instance for people and locations).

The process may be seen as progressively enriching the documents with new layers of annotations produced by various NLP modules and possibly validated by users, preferably in a collaborative way. It relies on the use of clearly identified representation formats for the annotations, as advocated within ISO TC 37/SC 4 standards and the TEI guidelines, but also on the existence of well-designed collaborative interfaces for browsing, querying, visualisation, and validation. ALMAnaCH has been or is working on several of the NLP bricks needed for setting such a work-flow, and has a solid expertise in the issues related to standardisation (of documents and annotations). However, putting all these elements in a unified work-flow that is simple to deploy and configure remains to be done. In particular, work-flow and interface should maybe not be dissociated, in the sense that the work-flow should be easily piloted and configured from the interface. An option will be to identify pertinent emerging platforms in DH (such as Transkribus) and to propose collaborations to ensure that NLP modules can be easily integrated.

It should be noted that such work-flows have actually a large potential besides DH, for instance for exploiting internal documentation (for a company) or exploring existing relationships between entities.

3.4.2 Development of Lexical Resources

ALPAGE, the Inria predecessor of ALMAnaCH, has put a strong emphasis in the development of morphological, syntactic and wordnet-like semantic lexical resources for French as well as other languages (see for instance 8, 1). Such resources play a crucial role in all NLP tools, as has been proven among other tasks for POS tagging 101, 103, 115 and parsing, and some of the lexical resource development will be targeted towards the improvement of NLP tools. They will also play a central role for studying diachrony in the lexicon, for example for Ancient to Contemporary French in the context of the Profiterole project. They will also be one of the primary sources of linguistic information for augmenting language models used in OCR systems for ancient scripts, and will allow us to develop automatic annotation tools (e.g. POS taggers) for low-resourced languages (see already 116), especially ancient languages. Finally, semantic lexicons such as wordnets will play a crucial role in assessing lexical similarity and automating etymological research.

Therefore, an important effort towards the development of new morphological lexicons will be initiated, with a focus on ancient languages of interest. Following previous work by ALMAnaCH members, we will try and leverage all existing resources whenever possible such as electronic dictionaries, OCRised dictionaries, both modern and ancient 100, 78, 102, while using and developing (semi)automatic lexical information extraction techniques based on existing corpora 104, 106. A new line of research will be to integrate the diachronic axis by linking lexicons that are in diachronic relation with one another thanks to phonetic and morphological change laws (e.g. XIIth century French with XVth century French and contemporary French). Another novelty will be the integration of etymological information in these lexical resources, which requires the formalisation, the standardisation, and the extraction of etymological information from OCRised dictionaries or other electronic resources, as well as the automatic generation of candidate etymologies. These directions of research are already investigated in ALMAnaCH 78, 102.

An underlying effort for this research will be to further the development of the GROBID-dictionaries software, which provides cascading CRF (Conditional Random Fields) models for the segmentation and analysis of existing print dictionaries. The first results we have obtained have allowed us to set up specific collaborations to improve our performances in the domains of a) recent general purpose dictionaries such as the Petit Larousse (Nénufar project, funded by the DGLFLF in collaboration with the University of Montpellier), b) etymological dictionaries (in collaboration with the Berlin Brandenburg Academy of sciences) and c) patrimonial dictionaries such as the Dictionnaire Universel de Basnage (an ANR project, including a PhD thesis at ALMAnaCH, has recently started on this topic in collaboration with the University of Grenoble-Alpes and the University Sorbonne Nouvelle in Paris).

In the same way as we signalled the importance of standards for the representation of interoperable corpora and their annotations, we will keep making the best use of the existing standardisation background for the representation of our various lexical resources. There again, the TEI guidelines play a central role, and we have recently participated in the “TEI Lex 0” initiative to provide a reference subset for the “Dictionary” chapter of the guidelines. We are also responsible, as project leader, of the edition of the new part 4 of the ISO standard 24613 (LMF, Lexical Markup Framework)  97 dedicated to the definition of the TEI serialisation of the LMF model (defined in ISO 24613 part 1 `Core model', 2 `Machine Readable Dictionaries' and 3 `Etymology'). We consider that contributing to standards allows us to stabilise our knowledge and transfer our competence.

3.4.3 Development of Annotated Corpora

Along with the creation of lexical resources, ALMAnaCH is also involved in the creation of corpora either fully manually annotated (gold standard) or automatically annotated with state-of-the-art pipeline processing chains (silver standard). Annotations will either be only morphosyntactic or will cover more complex linguistic levels (constituency and/or dependency syntax, deep syntax, maybe semantics). Former members of the ALPAGE project have a renowned experience in those aspects (see for instance 109, 96, 108, 87) and will participate to the creation of valuable resources originating from the historical domain genre.

Under the auspices of the ANR Parsiti project, led by ALMAnaCH (PI: DS), we aim to explore the interaction of extra-linguistic context and speech acts. Exploiting extra-linguistics context highlights the benefits of expanding the scope of current NLP tools beyond unit boundaries. Such information can be of spatial and temporal nature, for instance. They have been shown to improve Entity Linking over social media streams 72. In our case, we decided to focus on a closed world scenario in order to study context and speech acts interaction. To do so, we are developing a multimodal data set made of live sessions of a first person shooter video game (Alien vs. Predator) where we transcribed all human players interactions and face expressions streamlined with a log of all in-game events linked to the video recording of the game session, as well as the recording of the human players themselves. The in-games events are ontologically organised and enable the modelling of the extra-linguistics context with different levels of granularity. Recorded over many games sessions, we already transcribed over 2 hours of speech that will serve as a basis for exploratory work, needed for the prototyping of our context-enhanced NLP tools. In the next step of this line of work, we will focus on enriching this data set with linguistic annotations, with an emphasis on co-references resolutions and predicate argument structures. The midterm goal is to use that data set to validate a various range of approaches when facing multimodal data in a close-world environment.

6.1.1 Enqi

• Author: Benoît Sagot
• Contact: Benoît Sagot

6.1.2 SYNTAX

• Keyword: Parsing
• Functional Description: Syntax system includes various deterministic and non-deterministic CFG parser generators. It includes in particular an efficient implementation of the Earley algorithm, with many original optimizations, that is used in several of Alpage's NLP tools, including the pre-processing chain Sx Pipe and the LFG deep parser SxLfg . This implementation of the Earley algorithm has been recently extended to handle probabilistic CFG (PCFG), by taking into account probabilities both during parsing (beam) and after parsing (n-best computation).
• URL: http://syntax.gforge.inria.fr/
• Authors: Pierre Boullier, Philippe Deschamps, Benoît Sagot
• Contacts: Pierre Boullier, Benoît Sagot
• Participants: Benoît Sagot, Pierre Boullier

6.1.3 FRMG

• Keywords: Parsing, French
• Functional Description: FRMG is a large-coverage linguistic meta-grammar of French. It can be compiled (using MGCOMP) into a Tree Adjoining Grammar, which, in turn, can be compiled (using DyALog) into a parser for French.
• URL: http://mgkit.gforge.inria.fr/
• Contact: Éric De La Clergerie
• Participant: Eric de La Clergerie

6.1.4 MElt

• Name: Maximum-Entropy lexicon-aware tagger
• Keyword: Part-of-speech tagger
• Functional Description:

  MElt is a freely available (LGPL) state-of-the-art sequence labeller that is meant to be trained on both an annotated corpus and an external lexicon. It was developed by Pascal Denis and Benoît Sagot within the Alpage team, a joint INRIA and Université Paris-Diderot team in Paris, France. MElt allows for using multiclass Maximum-Entropy Markov models (MEMMs) or multiclass perceptrons (multitrons) as underlying statistical devices. Its output is in the Brown format (one sentence per line, each sentence being a space-separated sequence of annotated words in the word/tag format).

  MElt has been trained on various annotated corpora, using Alexina lexicons as source of lexical information. As a result, models for French, English, Spanish and Italian are included in the MElt package.

  MElt also includes a normalization wrapper aimed at helping processing noisy text, such as user-generated data retrieved on the web. This wrapper is only available for French and English. It was used for parsing web data for both English and French, respectively during the SANCL shared task (Google Web Bank) and for developing the French Social Media Bank (Facebook, twitter and blog data).

• URL: https://team.inria.fr/almanach/melt/
• Contact: Benoît Sagot

6.1.5 dyalog-sr

• Keywords: Parsing, Deep learning, Natural language processing
• Functional Description: DyALog-SR is a transition-based dependency parser, built on top of DyALog system. Parsing relies on dynamic programming techniques to handle beams. Supervised learning exploit a perceptron and aggressive early updates. DyALog-SR can handle word lattice and produce dependency graphs (instead of basic trees). It was tested during several shared tasks (SPMRL'2013 and SEMEVAL'2014). It achieves very good accuracy on French TreeBank, alone or by coupling with FRMG parser. In 2017, DyALog-SR has been extended into DyALog-SRNN by adding deep neuronal layers implemented with the Dynet library. The new version has participated to the evaluation campaigns CONLL UD 2017 (on more than 50 languages) and EPE 2017.
• Contact: Éric De La Clergerie

6.1.6 FSMB

• Name: French Social Media Bank
• Keywords: Treebank, User-generated content
• Functional Description: The French Social Media Bank is a treebank of French sentences coming from various social media sources (Twitter(c), Facebook(c)) and web forums (JeuxVidéos.com(c), Doctissimo.fr(c)). It contains different kind of linguistic annotations: - part-of-speech tags - surface syntactic representations (phrase-based representations) as well as normalized form whenever necessary.
• Contacts: Djamé Seddah, Benoît Sagot

6.1.7 DyALog

• Keyword: Logic programming
• Functional Description: DyALog provides an environment to compile and execute grammars and logic programs. It is essentially based on the notion of tabulation, i.e. of sharing computations by tabulating traces of them. DyALog is mainly used to build parsers for Natural Language Processing (NLP). It may nevertheless be used as a replacement for traditional PROLOG systems in the context of highly ambiguous applications where sub-computations can be shared.
• URL: http://dyalog.gforge.inria.fr/
• Contact: Eric de La Clergerie
• Participant: Eric de La Clergerie

6.1.8 SxPipe

• Keyword: Surface text processing
• Scientific Description: Developed for French and for other languages, Sx Pipe includes, among others, various named entities recognition modules in raw text, a sentence segmenter and tokenizer, a spelling corrector and compound words recognizer, and an original context-free patterns recognizer, used by several specialized grammars (numbers, impersonal constructions, quotations...). It can now be augmented with modules developed during the former ANR EDyLex project for analysing unknown words, this involves in particular (i) new tools for the automatic pre-classification of unknown words (acronyms, loan words...) (ii) new morphological analysis tools, most notably automatic tools for constructional morphology (both derivational and compositional), following the results of dedicated corpus-based studies. New local grammars for detecting new types of entities and improvement of existing ones, developed in the context of the PACTE project, will soon be integrated within the standard configuration.
• Functional Description: SxPipe is a modular and customizable processing chain dedicated to applying to raw corpora a cascade of surface processing steps (tokenisation, wordform detection, non-deterministic spelling correction…). It is used as a preliminary step before ALMAnaCH's parsers (e.g., FRMG) and for surface processing (named entities recognition, text normalization, unknown word extraction and processing...).
• URL: http://lingwb.gforge.inria.fr/
• Authors: Benoît Sagot, Pierre Boullier
• Contact: Benoît Sagot
• Participants: Benoît Sagot, Djamé Seddah, Eric de La Clergerie

6.1.9 Mgwiki

• Keywords: Parsing, French
• Functional Description: Mgwiki is a linguistic wiki that may used to discuss linguistic phenomena with the possibility to add annotated illustrative sentences. The work is essentially devoted to the construction of an instance for documenting and discussing FRMG, with the annotations of the sentences automatically provided by parsing them with FRMG. This instance also offers the possibility to parse small corpora with FRMG and an interface of visualization of the results. Large parsed corpora (like French Wikipedia or Wikisource) are also available. The parsed corpora can also be queried through the use of the DPath language.
• URL: http://alpage.inria.fr/frmgwiki/
• Contact: Eric de La Clergerie
• Participant: Eric de La Clergerie

6.1.10 WOLF

• Name: WOrdnet Libre du Français (Free French Wordnet)
• Keywords: WordNet, French, Semantic network, Lexical resource
• Functional Description:

  The WOLF (Wordnet Libre du Français, Free French Wordnet) is a free semantic lexical resource (wordnet) for French.

  The WOLF has been built from the Princeton WordNet (PWN) and various multilingual resources.

• URL: http://alpage.inria.fr/~sagot/wolf-en.html
• Contact: Benoît Sagot

6.1.11 vera

• Keyword: Text mining
• Functional Description: Automatic analysis of answers to open-ended questions based on NLP and statistical analysis and visualisation techniques (vera is currently restricted to employee surveys).
• Authors: Benoît Sagot, Dimitri Tcherniak
• Contact: Benoît Sagot
• Participants: Benoît Sagot, Dimitri Tcherniak
• Partner: Verbatim Analysis

6.1.12 Alexina

• Name: Atelier pour les LEXiques INformatiques et leur Acquisition
• Keyword: Lexical resource
• Functional Description: Alexina is ALMAnaCH's framework for the acquisition and modeling of morphological and syntactic lexical information. The first and most advanced lexical resource developed in this framework is the Lefff, a morphological and syntactic lexicon for French.
• URL: http://gforge.inria.fr/projects/alexina/
• Contact: Benoît Sagot
• Participant: Benoît Sagot

6.1.13 FQB

• Name: French QuestionBank
• Keyword: Treebank
• Functional Description:

  The French QuestionBanks is a corpus of around 2000 questions coming from various domains (TREC data set, French governmental organisation, NGOs, etc..) it contains different kind of annotations - morpho-syntactic ones (POS, lemmas) - surface syntaxe (phrase based and dependency structures) with long-distance dependency annotations.

  The TREC part is aligned with the English QuestionBank (Judge et al, 2006).

• Contacts: Djamé Seddah, Marie Candito

6.1.14 Sequoia corpus

• Keyword: Treebank
• Functional Description: The Sequoia corpus contains French sentences, annotated with various linguistic information: - parts-of-speech - surface syntactic representations (both constituency trees and dependency trees) - deep syntactic representations (which are deep syntactic dependency graphs)
• Contacts: Djamé Seddah, Marie Candito, Bruno Guillaume

9.1.1 FP7 & H2020 Projects

9.1.2 Collaborations in European Programs, except FP7 and H2020

9.1.3 ANR

9.1.4 Competitivity Clusters and Thematic Institutes

9.1.5 Other National Initiatives

9.1.6 Regional Initiatives

10.1.1 Scientific Events: Selection

10.1.2 Journal

10.1.3 Invited Talks

• Alix Chagué: ALFA Seminar on “Artificial intelligence for the analysis of the alfonsine corpus” at l'Observatoire de Paris, Paris, France (15 Dec 2020): “EScriptorium: an application for handwritten text recognition”.
• Éric de La Clergerie: GDR Lift workshop on “Linguistique informatique, formelle et de terrain” (11 Dec 2020): “SMG Simple MetaGrammars”.
• Pedro Javier Ortiz Suárez: Séminaires du Lattice, École normale supérieure / Laboratoire Lattice (22 Sep 2020): “Des Méthodes de TAL modernes pour l'Enrichissement de Documents”.
• Djamé Seddah:
  • Seminar at Axa REV (26 Apr 2020): “Deep Learning and the rise of CamemBERT”.
  • Invited talk at the Paris NLP Meetup (22 Jan 2020): “Sesame street-based naming schemes must fade out, long live CamemBERT et le French fromage!”.

10.1.4 Research Administration

• Pedro Javier Ortiz Suárez: Member of the user committee for the Jean Zay supercomputer (Invited member).
• Laurent Romary:
  • Member of the scientific board for the ELEXIS Interoperability and Sustainability Committee (ISC) (ELEXIS is the European Lexicographic Infrastructure.).
  • Member of the scientific board for the Schloss Dagstuhl Scientific Advisory Board (Website).
  • President of the scientific board for ABES (Website).
  • Member of the international advisory board for the Research Infrastructure project LINDAT/CLARIAH-CZ.
• Djamé Seddah: Member of the scientific board and Vice President of the French NLP society (ATALA).

10.2.1 Teaching

• Alix Chagué: Master's course (M1) as part of the Masters “Archives”, “Histoire” et “Lettres et langues”. Introduction à LaTeX (5 hours). Institut d’études culturelles et internationales (IECI), Université Versailles-Saint-Quentin-en-Yvelines, France.
• Alix Chagué: Master's course (M1) as part of the Masters “Archives”, “Histoire” et “Lettres et langues”. Introduction à Linux (5 hours). Institut d’études culturelles et internationales (IECI), Université Versailles-Saint-Quentin-en-Yvelines, France.
• Alix Chagué: Master's course (M2) as part of the Master “Technologies Numériques Appliquées à l'Histoire”. Introduction à la programmation avec Python (10 hours). École nationale des chartes, France.
• Alix Chagué: Master's course (M2) as part of the Master “Documentation et Humanités Numériques”. Typologie, formats et outils d'exploitation des documents numériques : introduction à XML TEI (6 hours). École du Louvre, France.
• Alix Chagué: Master's course (M2) as part of the Master “Documentation et Humanités Numériques”. Introduction à Python et à l'algorithmie (6 hours). École du Louvre, France.
• Louis Martin: Master's course (M2) as part of the Master “Mathématiques, Vision Apprentissage”. Speech and Language Processing (3 hours), coorganised with Vincent Lepetit. ENS Paris-Saclay, France.
• Alix Chagué: Master's course (M2) as part of the Master “Documentation et Humanités Numériques”. Méthodologie de la recherche et préprofessionalisation (18 hours). École du Louvre, France.
• Clémentine Fourrier: Eq. Master's course (M1,M2) Module TDLog - Techniques de Developpement Logiciel (computer science course in Python) (18 hours). École des Ponts ParisTech, France.
• Clémentine Fourrier: Eq. Master's course (M1,M2) Module TDLog - Techniques de Developpement Logiciel (computer science course in Python) (12.25 hours). École des Ponts ParisTech, France.
• Loïc Grobol: Master's course (M1) as part of the pluriTAL. Introduction à la fouille de textes (39 hours). Université Sorbonne Nouvelle, France.
• Louis Martin: Master's course (M2) as part of the African Master's in Machine Intelligence. Deep Natural Language Processing (25 hours), coorganised with Antoine Bordes and Angela Fan. Kigali, Rwanda.
• Mathilde Regnault: Bachelor's course (L2) as part of the Licence Sciences du langage. Informatique et industries de la langue (20 hours). Université Sorbonne Nouvelle, Paris, France.
• Pedro Javier Ortiz Suárez: Bachelor's course (L2) as part of the Licence de Sciences et Technologies. Eléments de programmation 2 (None hours). Sorbonne Université, Paris, France.
• Pedro Javier Ortiz Suárez: Bachelor's course (L2) as part of the Licence de Sciences et Technologies. Mathématiques discrètes (40 hours). Sorbonne Université, Paris, France.
• Benoît Sagot: Master's course (M2) as part of the Master “Mathématiques, Vision Apprentissage”. Speech and Language Processing (20 hours), coorganised with Emmanuel Dupoux. ENS Paris-Saclay, France.
• Alix Chagué: Animated eScriptorium Tutorial, Online (1 Oct 2020): Prise en main d'eScriptorium (2.5 hours)
• Clémentine Fourrier: Animated Coding dojo, ENPC Paris (1 Sep 2020): TDLOG coding dojo, coorganised with Theodo (CS startup) (6 hours)

10.2.2 Supervision

• PhD defended: Mohamed Khemakhem, “Automatic extraction of lexical content and structure from digitized legacy dictionaries” (1 Sep 2016–31 Aug 2020). Supervised by Laurent Romary. PhD defended on 1 Oct 2020.
• PhD defended: Jack Bowers, “Corpus and lexicon for Mixtec, TEI” (1 Oct 2016–8 Oct 2020). Supervised by Laurent Romary. PhD defended on 8 Oct 2020.
• PhD defended: Loïc Grobol, “Coreference resolution” (1 Oct 2016–15 Jul 2020). Supervised by Frédéric Landragin, Marco Dinarelli and Éric de La Clergerie. PhD defended on 15 Jul 2020.
• PhD in progress: Axel Herold, “Extraction of etymological information from digital dictionaries” (1 Oct 2016–present). Supervised by Laurent Romary.
• PhD in progress: Mathilde Regnault, “Medieval French processing” (1 Oct 2017–15 Sep 2020). Supervised by Sophie Prévost and Éric de La Clergerie.
• PhD in progress: Louis Martin, “Automatic text simplification” (1 Jun 2018–present). Supervised by Benoît Sagot and Éric de La Clergerie.
• PhD in progress: José Carlos Rosales Núñez, “Machine translation for user-generated content” (1 Jun 2018–present). Supervised by Guillaume Wisniewksi and Djamé Seddah.
• PhD in progress: Pedro Javier Ortiz Suárez, “NLP and IE from 17th century encyclopedia” (1 Oct 2018–present). Supervised by Laurent Romary and Benoît Sagot.
• PhD in progress: Benjamin Muller, “NLP for social media texts” (1 Oct 2018–present). Supervised by Benoît Sagot and Djamé Seddah.
• PhD in progress: Clémentine Fourrier, “Neural architecture development, computational historical linguistics” (1 Oct 2019–present). Supervised by Laurent Romary, Benoît Sagot and Rachel Bawden.
• PhD in progress: Robin Algayres, “Unsupervised Automatic Speech Recognition in low resource conditions” (1 Oct 2019–present). Supervised by Emmanuel Dupoux and Benoît Sagot.
• PhD in progress: Lionel Tadjou Tadonfouet, “Conversations Disentanglement” (1 Mar 2020–present). Supervised by Laurent Romary and Éric de La Clergerie.

10.2.3 Juries

• Kim Gerdes: Reviewer of the PhD committee for Mohammed Galal at the University of Ain Shams, Egypt on 8 Jan 2020. Title: Les constructions exceptives du français et de l’arabe : syntaxe et interface sémantique-syntaxe
• Kim Gerdes: President of the PhD committee for Marie-Amélie Botalla at the Université Sorbonne Nouvelle, Paris, France on 14 May 2020. Title: Modélisation de la production des énoncés averbaux : le cas des compléments différés
• Benoît Sagot: Reviewer of the PhD committee for Alice Millour at the Sorbonne Université, Paris, France on 14 Dec 2020. Title: Myriadisation de ressources linguistiques pour le traitement automatique de langues non-standardisées
• Benoît Sagot: Examiner of the Master committee for Antoine Yang at the École Polytechnique & ENS Paris-Saclay, France on 12 Sep 2020. Title: Leveraging large scale video data for Video Question Answering
• Benoît Sagot: Examiner of the PhD committee for Jack Bowers at the Université Paris Sciences et Lettres on 8 Oct 2020. Title: Language Documentation and Standards in Digital Humanities: TEI and the documentation of Mixtepec-Mixtec
• Benoît Sagot: Reviewer of the PhD committee for Jacobo Levy Abitbol at the ENS de Lyon on 9 Jan 2020. Title: Computational detection of socioeconomic inequalities
• Benoît Sagot: Examiner of the Master committee for Lucas Elbert at the ENS Paris-Saclay on 10 Sep 2020. Title: Explorations with a voice-type classifier for child-centered audio recordings
• Alix Chagué: Examiner of the Master committee for Lucas Terriel at the Ecole nationale des chartes on 19 Oct 2020. Title: Représenter et évaluer les données issues du traitement automatique d’un corpus de documents historiques. L’exemple de la reconnaissance des écritures manuscrites dans les répertoires de notaires du projet LectAuRep.
• Alix Chagué: Examiner of the Master committee for Jean-Damien Genero at the Ecole nationales des chartes on 19 Oct 2020. Title: Valoriser le traitement automatique des données : Le cas des Ouvriers des deux mondes
• Éric de La Clergerie: Examiner of the PhD committee for Loïc Grobol at the Université Sorbonne Nouvelle, Paris, France on 15 Jul 2020. Title: Coreference resolution for spoken French

10.3.1 Articles and contents

10.3.2 Education

• Clémentine Fourrier participated in “Filles et Maths, une équation lumineuse”. Sorbonne, 1 May 2020 (2 hours).
• Clémentine Fourrier participated in “Filles et Maths, une équation lumineuse”. Online, 1 Aug 2020 (2 hours).
• Clémentine Fourrier, with Eloise Berthier, was the main organiser of “Rendez-Vous des Jeunes Mathématiciennes et Informaticiennes Inria 2020”. Inria Paris and online, 1 Oct 2020 (14 hours).
• Rachel Bawden participated in “Rendez-Vous des Jeunes Mathématiciennes et Informaticiennes Inria 2020”. Inria Paris and online, 1 Oct 2020 (1 hour).
• Pedro Javier Ortiz Suárez participated in “Rendez-Vous des Jeunes Mathématiciennes et Informaticiennes Inria 2020”. Inria Paris and online, 1 Oct 2020 (6 hours).
• Clémentine Fourrier participated in “Rendez-Vous des Jeunes Mathématiciennes et Informaticiennes ENS 2020”. Online for the ENS, 1 Dec 2020 (2 hours).

10.3.3 Interventions

• Éric de La Clergerie gave a talk at “AI Paris 2020”. Paris Porte de Versailles, 14 Sep 2020 (1 hour).
• Éric de La Clergerie gave a talk at the “Seminaire Club Speech Bertin IT”. Paris, 13 Oct 2020 (1 hour).
• Benoît Sagot gave a talk at “France is AI”. Online, 16 Nov 2020.
• Éric de La Clergerie participated in “Battle Lab Rens”. Online, 25 Nov 2020 (20 hours).
• Alix Chagué, with ADEMEC (Association des Diplômés et Etudiants des Masters de l'Ecole des chartes), was the main organiser of “ADEMEC Monthly Workshops”. Ecole nationale des chartes, 1 Dec 2020 (2 hours).

International journals

• 14 article AndreaA. Bertino, LucaL. Foppiano, LaurentL. Romary and PierreP. Mounier. Leveraging Concepts in Open Access Publications Journal of Data Mining and Digital Humanities 2019 June 2020
  HAL back to text
• 15 articleXinyingX. Chen and KimK. Gerdes. Dependency Distances and Their Frequencies in Indo-European LanguageJournal of Quantitative LinguisticsJune 2020, 1-20
  HALDOI
• 16 articleLucaL. Foppiano and LaurentL. Romary. Entity-fishing: a DARIAH entity recognition and disambiguation serviceJournal of the Japanese Association for Digital Humanities51November 2020, 22-60
  HALDOIback to text

International peer-reviewed conferences

• 17 inproceedings RobinR. Algayres, Mohamed SalahM. Zaiem, BenoîtB. Sagot and EmmanuelE. Dupoux. Evaluating the reliability of acoustic speech embeddings INTERSPEECH 2020 - Annual Conference of the International Speech Communication Association Shanghai / Vitrtual, China October 2020
  HAL
• 18 inproceedings FernandoF. Alva-Manchego, LouisL. Martin, AntoineA. Bordes, CarolinaC. Scarton, BenoîtB. Sagot and LuciaL. Specia. ASSET: A Dataset for Tuning and Evaluation of Sentence Simplification Models with Multiple Rewriting Transformations ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics Seattle / Virtual, United States July 2020
  HAL back to text
• 19 inproceedings FaridF. Arthaud, RachelR. Bawden and AlexandraA. Birch. Few-shot learning through contextual data augmentation EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics Proceedings of the 16th conference of the European Chapter of the Association for Computational Linguistics Kiev / Virtual, Ukraine April 2021
  HAL
• 20 inproceedings MurielleM. Fabre, Pedro JavierP. Ortiz Suárez, BenoîtB. Sagot and ÉricÉ. Villemonte de La Clergerie. French Contextualized Word-Embeddings with a sip of CaBeRnet: a New French Balanced Reference Corpus CMLC-8 - 8th Workshop on the Challenges in the Management of Large Corpora Marseille, France https://lrec2020.lrec-conf.org/media/proceedings/Workshops/Books/CMLC-8book.pdf May 2020
  HAL
• 21 inproceedings ClémentineC. Fourrier and BenoîtB. Sagot. Comparing Statistical and Neural Models for Learning Sound Correspondences LT4HALA 2020 : First Workshop on Language Technologies for Historical and Ancient Languages Marseille, France May 2020
  HAL back to text back to text
• 22 inproceedings ClémentineC. Fourrier and BenoîtB. Sagot. Methodological Aspects of Developing and Managing an Etymological Lexical Resource: Introducing EtymDB 2.0 LREC 2020 - 12th Language Resources and Evaluation Conference Marseille, France May 2020
  HAL back to text
• 23 inproceedings SimonS. Gabay, LucieL. Rondeau Du Noyer and MohamedM. Khemakhem. Selling autograph manuscripts in 19th c. Paris: digitising the Revue des Autographes IX Convegno AIUCD Milan, Italy https://aiucd2020.unicatt.it January 2020
  HAL
• 24 inproceedingsHilaH. Gonen, GaneshG. Jawahar, DjaméD. Seddah and YoavY. Goldberg. Simple, Interpretable and Stable Method for Detecting Words with Usage Change across CorporaACL 2020 - 58th Annual Meeting of the Association for Computational LinguisticsSeattle / Virtual, United StatesJuly 2020, 538-555
  HALDOIback to text
• 25 inproceedings GaëlG. Guibon, MarineM. Courtin, KimK. Gerdes and BrunoB. Guillaume. When Collaborative Treebank Curation Meets Graph Grammars: Arborator With a Grew Back-End LREC 2020 - 12th Language Resources and Evaluation Conference Marseille, France http://www.lrec-conf.org/proceedings/lrec2020/index.html May 2020
  HAL
• 26 inproceedingsGaëlG. Guibon and BenoîtB. Sagot. OFrLex: A Computational Morphological and Syntactic Lexicon for Old FrenchLREC 2020 - 12th Language Resources and Evaluation ConferenceMarseille, FranceMay 2020, 11–16
  HALback to text
• 27 inproceedings FahadF. Khan, LaurentL. Romary, AnaA. Salgado, JackJ. Bowers, MohamedM. Khemakhem and TomaT. Tasovac. Modelling Etymology in LMF/TEI: The Grande Dicionário Houaiss da Língua Portuguesa Dictionary as a Use Case LREC 2020 - 12th Language Resources and Evaluation Conference Marseille, France http://www.lrec-conf.org May 2020
  HAL back to text
• 28 inproceedings TantiT. Kristanti and LaurentL. Romary. DeLFT and entity-fishing : Tools for CLEF HIPE 2020 Shared Task CLEF 2020 - Conference and Labs of the Evaluation Forum 2696 CLEF 2020 Working Notes Thessaloniki / Virtual, Greece http://ceur-ws.org/Vol-2696/ September 2020
  HAL back to text
• 29 inproceedings LouisL. Martin, BenjaminB. Muller, Pedro JavierP. Ortiz Suárez, YoannY. Dupont, LaurentL. Romary, ÉricÉ. Villemonte de La Clergerie, DjaméD. Seddah and BenoîtB. Sagot. CamemBERT: a Tasty French Language Model ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics Seattle / Virtual, United States July 2020
  HAL DOI back to text
• 30 inproceedings LouisL. Martin, ÉricÉ. Villemonte de La Clergerie, BenoîtB. Sagot and AntoineA. Bordes. Controllable Sentence Simplification LREC 2020 - 12th Language Resources and Evaluation Conference Marseille, France http://www.lrec-conf.org/proceedings/lrec2020/index.html May 2020
  HAL
• 31 inproceedings Pedro JavierP. Ortiz Suárez, YoannY. Dupont, GaëlG. Lejeune and TianT. Tian. SinNer@Clef-Hipe2020 : Sinful adaptation of SotA models for Named Entity Recognition in French and German CLEF 2020 Working Notes. Working Notes of CLEF 2020 - Conference and Labs of the Evaluation Forum Thessaloniki / Virtual, Greece https://impresso.github.io/CLEF-HIPE-2020/ October 2020
  HAL back to text
• 32 inproceedings Pedro JavierP. Ortiz Suárez, YoannY. Dupont, BenjaminB. Muller, LaurentL. Romary and BenoîtB. Sagot. Establishing a New State-of-the-Art for French Named Entity Recognition LREC 2020 - 12th Language Resources and Evaluation Conference Marseille, France http://www.lrec-conf.org May 2020
  HAL
• 33 inproceedings Pedro JavierP. Ortiz Suárez, LaurentL. Romary and BenoîtB. Sagot. A Monolingual Approach to Contextualized Word Embeddings for Mid-Resource Languages ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics Seattle / Virtual, United States https://acl2020.org July 2020
  HAL DOI back to text
• 34 inproceedings DjaméD. Seddah, FarahF. Essaidi, AmalA. Fethi, MatthieuM. Futeral, BenjaminB. Muller, Pedro JavierP. Ortiz Suárez, BenoîtB. Sagot and AbhishekA. Srivastava. Building a User-Generated Content North-African Arabizi Treebank: Tackling Hell ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics Seattle / Virtual, Canada July 2020
  HAL DOI back to text

National peer-reviewed Conferences

• 35 inproceedingsClémentineC. Fourrier. Sound change and neural networks: preliminary experimentsActes de la 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 3 : Rencontre des Étudiants Chercheurs en Informatique pour le TALJEP-TALN-RECITAL 2020 - 33ème Journées d’Études sur la Parole, 27ème Conférence sur le Traitement Automatique des Langues Naturelles, 22ème Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des LanguesNancy / Virtuel, France2020, 110-122
  HAL
• 36 inproceedings AntoineA. Gérard, BenoîtB. Sagot and EmilieE. Pons. Le Traitement Automatique des Langues au service du vin Dataquitaine 2021 - IA, Recherche Opérationnelle & Data Science Bordeaux / Virtual, France February 2021
  HAL
• 37 inproceedingsLouisL. Martin, BenjaminB. Muller, Pedro JavierP. Ortiz Suárez, YoanY. Dupont, LaurentL. Romary, EricE. Villemonte de la Clergerie, BenoîtB. Sagot and DjaméD. Seddah. CAMEMBERT Contextual Language Models for French: Impact of Training Data Size andHeterogeneityActes de la 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 2 : Traitement Automatique des Langues NaturellesJEP-TALN-RECITAL 2020 - 33ème Journées d’Études sur la Parole, 27ème Conférence sur le Traitement Automatique des Langues Naturelles, 22ème Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des LanguesNancy / Virtuel, France2020, 54-65
  HALback to text

Conferences without proceedings

• 38 inproceedings MohamedM. Khemakhem, SimonS. Gabay, BéatriceB. Joyeux-Prunel, LaurentL. Romary, LéaL. Saint-Raymond and LucieL. Rondeau Du Noyer. Information Extraction Workflow for Digitised Entry-based Documents DARIAH Annual event 2020 Zagreb / Virtual, Croatia https://dariah-ae-2020.sciencesconf.org/ May 2020
  HAL back to text

Scientific book chapters

• 39 inbook AnneA. Baillot. Zahlenwahn oder Textliebe? Digitale Philologie als Disziplin und als Weltanschauung Machines/Maschinen. Les machines dans l'espace germanique: de l'automate de Kempelen à Kraftwerk p. 379-388 Nantes, France September 2020
  HAL
• 40 inbookJenniferJ. Edmond, FrankF. Fischer, LaurentL. Romary and TomaT. Tasovac. 9. Springing the Floor for a Different Kind of Dance: Building DARIAH as a Twenty-First-Century Research Infrastructure for the Arts and HumanitiesDigital Technology and the Practices of Humanities ResearchFebruary 2020, 207-234
  HALDOIback to text
• 41 inbookJenniferJ. Edmond and LaurentL. Romary. 3. Academic PublishingDigital Technology and the Practices of Humanities ResearchFebruary 2020, 49-80
  HALDOIback to text

Doctoral dissertations and habilitation theses

• 42 thesis JackJ. Bowers. Language Documentation and Standards in Digital Humanities: TEI and the documentation of Mixtepec-Mixtec École Pratique des Hauts Études October 2020
  HAL back to text
• 43 thesis LoïcL. Grobol. Coreference resolution for spoken French Université Sorbonne Nouvelle - Paris 3 July 2020
  HAL
• 44 thesis MohamedM. Khemakhem. Standard-based Lexical Models for Automatically Structured Dictionaries Université de Paris October 2020
  HAL back to text

Reports & preprints

• 45 misc JackJ. Bowers, AxelA. Herold, LaurentL. Romary and TomaT. Tasovac. TEI Lex-0 Etym – towards terse recommendations for the encoding of etymological information January 2021
  HAL
• 46 misc JackJ. Bowers. Pathways and patterns of metaphor and metonymy in Mixtepec-Mixtec body-part terms June 2020
  HAL
• 47 report FlorianeF. Chiffoleau. Rapport d'avancement sur le projet DAHN (avec le soutien du MESRI) Inria Paris May 2020
  HAL
• 48 misc LucaL. Foppiano, SaeS. Dieb, AkiraA. Suzuki, PedroP. Baptista de Castro, SuguruS. Iwasaki, AzusaA. Uzuki, Miren GarbineM. Esparza Echevarria, YanY. Meng, KenseiK. Terashima, LaurentL. Romary, YoshihikoY. Takano and MasashiM. Ishii. SuperMat: Construction of a linked annotated dataset from superconductors-related publications January 2021
  HAL
• 49 misc LouisL. Martin, AngelaA. Fan, ÉricÉ. de la Clergerie, AntoineA. Bordes and BenoîtB. Sagot. Multilingual Unsupervised Sentence Simplification January 2021
  HAL back to text
• 50 misc BenjaminB. Muller, AntonisA. Anastasopoulos, BenoîtB. Sagot and DjaméD. Seddah. When Being Unseen from mBERT is just the Beginning: Handling New Languages With Multilingual Language Models October 2020
  HAL back to text
• 51 misc BenjaminB. Muller, YanaiY. Elazar, BenoîtB. Sagot and DjaméD. Seddah. First Align, then Predict: Understanding the Cross-Lingual Ability of Multilingual BERT March 2021
  HAL
• 52 misc BenjaminB. Muller, BenoîtB. Sagot and DjaméD. Seddah. Can Multilingual Language Models Transfer to an Unseen Dialect? A Case Study on North African Arabizi March 2021
  HAL
• 53 misc ArijA. Riabi, ThomasT. Scialom, RachelR. Keraron, BenoîtB. Sagot, DjaméD. Seddah and JacopoJ. Staiano. Synthetic Data Augmentation for Zero-Shot Cross-Lingual Question Answering January 2021
  HAL
• 54 misc ErzsébetE. Tóth-Czifra and LaurentL. Romary. The Heritage Data Reuse Charter: from principles to research workflows February 2020
  HAL
• 55 misc NaomiN. Truan and LaurentL. Romary. Building, Encoding, and Annotating a Corpus of Parliamentary Debates in XML-TEI: A Cross-Linguistic Account June 2020
  HAL

Other scientific publications

• 56 misc Jean-DamienJ.-D. Généro. Le corpus des Ouvriers des deux mondes : des images et des URLs June 2020
  HAL
• 57 misc LaurentL. Romary. An editorial and technical journey into Post Publication Peer Review (PPPR) Berlin / Virtual, Germany October 2020
  HAL back to text
• 58 misc LaurentL. Romary. Multilingual content management and standards with a view on AI developments Turin / Virtual, Italy October 2020
  HAL back to text
• 59 misc LaurentL. Romary. TEI guidelines: born to be open Vienne, Austria June 2020
  HAL back to text
• 60 misc LucasL. Terriel. Le saviez-vous ? Les répertoires de notaires ne sont pas seulement des images numérisées ! October 2020
  HAL

Scientific popularization

• 61 inproceedings A. Chagué and R. Aurélia. Présentation du projet Lectaurep (Lecture automatique de répertoires) Atelier sur la transcription des écritures manuscrites - BnF DataLab Paris, France January 2021
  HAL
• 62 misc A. Chagué, L. Terriel and L. Romary. Des images au texte : LECTAUREP, un projet de reconnaissance automatique d'écriture Lille / Virtual, France November 2020
  HAL back to text
• 63 article L. Romary. Découpler gestion des manuscrits de publication et évaluation par les pairs : la plateforme de gestion de revues Épisciences I2D – Information, données & documents 2 2020
  HAL back to text
• 64 misc L. Romary. Les données de la recherche Nancy / Virtual, France November 2020
  HAL back to text