Conversational grounding, vital for building dependable dialog systems, involves ensuring a mutual understanding of shared information. Despite its importance, there has been limited research on this aspect of conversation in recent years, especially after the advent of Large Language Models (LLMs). Previous studies have highlighted the shortcomings of pre-trained language models in conversational grounding. However, most testing for conversational grounding capabilities involves human evaluations that are costly and time-consuming. This has led to a lack of testing across multiple models of varying sizes, a critical need given the rapid rate of new model releases. This gap in research becomes more significant considering recent advances in language models, which have led to new emergent capabilities. In this paper, we aim to evaluate the performance of LLMs in various aspects of conversational grounding and analyze why some models perform better than others. We demonstrate a direct correlation between the size of the pre-training data and conversational grounding abilities, meaning that they have independently acquired a specific form of pragmatic capabilities from larger pre-training datasets. Finally, we propose ways to enhance the capabilities of the models that lag in this aspect.

The improvements in neural machine translation make translation and post-editing pipelines ever more effective for a wider range of applications. In this paper, we evaluate the effectiveness of such a pipeline for the translation of scientific documents (limited here to article abstracts). Using a dedicated interface, we collect, then analyse the post-edits of approximately 350 abstracts (English→French) in the Natural Language Processing domain for two groups of post-editors: domain experts (academics encouraged to post-edit their own articles) on the one hand and trained translators on the other. Our results confirm that such pipelines can be effective, at least for high-resource language pairs. They also highlight the difference in the post-editing strategy of the two subgroups. Finally, they suggest that working on term translation is the most pressing issue to improve fully automatic translations, but that in a post-editing setup, other error types can be equally annoying for post-editors.

Successful conversations often rest on common understanding, where all parties are on the same page about the information being shared. This process, known as conversational grounding, is crucial for building trustworthy dialog systems that can accurately keep track of and recall the shared information. The proficiencies of an agent in grounding the conveyed information significantly contribute to building a reliable dialog system. Despite recent advancements in dialog systems, there exists a noticeable deficit in their grounding capabilities. Traum (Traum, 1995) provided a framework for conversational grounding introducing Grounding Acts and Grounding Units, but substantial progress, especially in the realm of Large Language Models, remains lacking. To bridge this gap, we present the annotation of two dialog corpora employing Grounding Acts, Grounding Units, and a measure of their degree of grounding. We discuss our key findings during the annotation and also provide a baseline model to test the performance of current Language Models in categorizing the grounding acts of the dialogs. Our work aims to provide a useful resource for further research in making conversations with machines better understood and more reliable in natural day-to-day collaborative dialogs.

In this article we look at how two different standards for lexical resources, TEI and OntoLex, deal with corpus citations in lexicons. We will focus on how corpus citations in retrodigitised dictionaries can be modelled using each of the two standards since this provides us with a suitably challenging use case. After looking at the structure of an example entry from a legacy dictionary, we examine the two approaches offered by the two different standards by outlining an encoding for the example entry using both of them (note that this article features the first extended discussion of how the Frequency Attestation and Corpus (FrAC) module of OntoLex deals with citations). After comparing the two approaches and looking at the advantages and disadvantages of both, we argue for a combination of both. In the last part of the article we discuss different ways of doing this, giving our preference for a strategy which makes use of RDFa.

Data modeling and standardization are central issues in the field of Digital Humanities, and all the more so when dealing with Holocaust testimonies, where stable preservation and long-term accessibility are key. The EHRI Online Editions are composed of documents of diverse nature (testimonies, letters, diplomatic reports, etc.), held by EHRI’s partnering institutions, and selected, gathered thematically and encoded according to the TEI Guidelines by the editors within the EHRI Consortium. Standardization is essential in order to make sure that the editions are consistent with one another. The issue of consistency also encourages a broader reflection on the usage of standards when processing data, and on the standardization of digital scholarly editions of textual documents in general. In this paper, we present the normalization work we carried out on the EHRI Online Editions. It includes a customization of the TEI adapted to Holocaust-related documents, and a focus on the implementation of controlled vocabulary. We recommend the use of these encoding specifications as a tool for researchers and/or non-TEI experts to ensure their encoding is valid and consistent across editions, but also as a mechanism for integrating the edition work smoothly within a wider workflow leading from image digitization to publication.

Les données cliniques dans les hôpitaux sont de plus en plus accessibles pour la recherche à travers les entrepôts de données de santé, cependant ces documents sont non-structurés. Il est donc nécessaire d’extraire les informations des comptes-rendus médicaux. L’utilisation du transfert d’apprentissage grâce à des modèles de type BERT comme CamemBERT ont permis des avancées majeures, notamment pour la reconnaissance d’entités nommées. Cependant, ces modèles sont entraînés pour le langage courant et sont moins performants sur des données biomédicales. C’est pourquoi nous proposons un nouveau jeu de données biomédical public français sur lequel nous avons poursuivi le pré-entraînement de CamemBERT. Ainsi, nous présentons une première version de CamemBERT-bio, un modèle public spécialisé pour le domaine biomédical français qui montre un gain de 2,54 points de F-mesure en moyenne sur différents jeux d’évaluations de reconnaissance d’entités nommées biomédicales.

Cette contribution présente le projet MaTOS (Machine Translation for Open Science), qui vise à développer de nouvelles méthodes pour la traduction automatique (TA) intégrale de documents scientifiques entre le français et l’anglais, ainsi que des métriques automatiques pour évaluer la qualité des traductions produites. Pour ce faire, MaTOS s’intéresse (a) au recueil de ressources ouvertes pour la TA spécialisée; (b) à la description des marqueurs de cohérence textuelle pour les articles scientifiques; (c) au développement de nouvelles méthodes de traitement multilingue pour les documents; (d) aux métriques mesurant les progrès de la traduction de documents complets.

The successes of contextual word embeddings learned by training large-scale language models, while remarkable, have mostly occurred for languages where significant amounts of raw texts are available and where annotated data in downstream tasks have a relatively regular spelling. Conversely, it is not yet completely clear if these models are also well suited for lesser-resourced and more irregular languages. We study the case of Old French, which is in the interesting position of having relatively limited amount of available raw text, but enough annotated resources to assess the relevance of contextual word embedding models for downstream NLP tasks. In particular, we use POS-tagging and dependency parsing to evaluate the quality of such models in a large array of configurations, including models trained from scratch from small amounts of raw text and models pre-trained on other languages but fine-tuned on Medieval French data.

The need for large corpora raw corpora has dramatically increased in recent years with the introduction of transfer learning and semi-supervised learning methods to Natural Language Processing. And while there have been some recent attempts to manually curate the amount of data necessary to train large language models, the main way to obtain this data is still through automatic web crawling. In this paper we take the existing multilingual web corpus OSCAR and its pipeline Ungoliant that extracts and classifies data from Common Crawl at the line level, and propose a set of improvements and automatic annotations in order to produce a new document-oriented version of OSCAR that could prove more suitable to pre-train large generative language models as well as hopefully other applications in Natural Language Processing and Digital Humanities.

In this paper we describe the process of build-ing a corporate corpus that will be used as a ref-erence for modelling and computing threadsfrom conversations generated using commu-nication and collaboration tools. The overallgoal of the reconstruction of threads is to beable to provide value to the collorator in var-ious use cases, such as higlighting the impor-tant parts of a running discussion, reviewingthe upcoming commitments or deadlines, etc. Since, to our knowledge, there is no avail-able corporate corpus for the French languagewhich could allow us to address this prob-lem of thread constitution, we present here amethod for building such corpora includingdifferent aspects and steps which allowed thecreation of a pipeline to pseudo-anonymisedata. Such a pipeline is a response to theconstraints induced by the General Data Pro-tection Regulation GDPR in Europe and thecompliance to the secrecy of correspondence.

In this article we will introduce two of the new parts of the new multi-part version of the Lexical Markup Framework (LMF) ISO standard, namely part 3 of the standard (ISO 24613-3), which deals with etymological and diachronic data, and Part 4 (ISO 24613-4), which consists of a TEI serialisation of all of the prior parts of the model. We will demonstrate the use of both standards by describing the LMF encoding of a small number of examples taken from a sample conversion of the reference Portuguese dictionary Grande Dicionário Houaiss da Língua Portuguesa, part of a broader experiment comprising the analysis of different, heterogeneously encoded, Portuguese lexical resources. We present the examples in the Unified Modelling Language (UML) and also in a couple of cases in TEI.

The French TreeBank developed at the University Paris 7 is the main source of morphosyntactic and syntactic annotations for French. However, it does not include explicit information related to named entities, which are among the most useful information for several natural language processing tasks and applications. Moreover, no large-scale French corpus with named entity annotations contain referential information, which complement the type and the span of each mention with an indication of the entity it refers to. We have manually annotated the French TreeBank with such information, after an automatic pre-annotation step. We sketch the underlying annotation guidelines and we provide a few figures about the resulting annotations.

We use the multilingual OSCAR corpus, extracted from Common Crawl via language classification, filtering and cleaning, to train monolingual contextualized word embeddings (ELMo) for five mid-resource languages. We then compare the performance of OSCAR-based and Wikipedia-based ELMo embeddings for these languages on the part-of-speech tagging and parsing tasks. We show that, despite the noise in the Common-Crawl-based OSCAR data, embeddings trained on OSCAR perform much better than monolingual embeddings trained on Wikipedia. They actually equal or improve the current state of the art in tagging and parsing for all five languages. In particular, they also improve over multilingual Wikipedia-based contextual embeddings (multilingual BERT), which almost always constitutes the previous state of the art, thereby showing that the benefit of a larger, more diverse corpus surpasses the cross-lingual benefit of multilingual embedding architectures.

Pretrained language models are now ubiquitous in Natural Language Processing. Despite their success, most available models have either been trained on English data or on the concatenation of data in multiple languages. This makes practical use of such models –in all languages except English– very limited. In this paper, we investigate the feasibility of training monolingual Transformer-based language models for other languages, taking French as an example and evaluating our language models on part-of-speech tagging, dependency parsing, named entity recognition and natural language inference tasks. We show that the use of web crawled data is preferable to the use of Wikipedia data. More surprisingly, we show that a relatively small web crawled dataset (4GB) leads to results that are as good as those obtained using larger datasets (130+GB). Our best performing model CamemBERT reaches or improves the state of the art in all four downstream tasks.

Les modèles de langue neuronaux contextuels sont désormais omniprésents en traitement automatique des langues. Jusqu’à récemment, la plupart des modèles disponibles ont été entraînés soit sur des données en anglais, soit sur la concaténation de données dans plusieurs langues. L’utilisation pratique de ces modèles — dans toutes les langues sauf l’anglais — était donc limitée. La sortie récente de plusieurs modèles monolingues fondés sur BERT (Devlin et al., 2019), notamment pour le français, a démontré l’intérêt de ces modèles en améliorant l’état de l’art pour toutes les tâches évaluées. Dans cet article, à partir d’expériences menées sur CamemBERT (Martin et al., 2019), nous montrons que l’utilisation de données à haute variabilité est préférable à des données plus uniformes. De façon plus surprenante, nous montrons que l’utilisation d’un ensemble relativement petit de données issues du web (4Go) donne des résultats aussi bons que ceux obtenus à partir d’ensembles de données plus grands de deux ordres de grandeurs (138Go).

Keyphrase extraction is the task of finding phrases that represent the important content of a document. The main aim of keyphrase extraction is to propose textual units that represent the most important topics developed in a document. The output keyphrases of automatic keyphrase extraction methods for test documents are typically evaluated by comparing them to manually assigned reference keyphrases. Each output keyphrase is considered correct if it matches one of the reference keyphrases. However, the choice of the appropriate textual unit (keyphrase) for a topic is sometimes subjective and evaluating by exact matching underestimates the performance. This paper presents a dataset of evaluation scores assigned to automatically extracted keyphrases by human evaluators. Along with the reference keyphrases, the manual evaluations can be used to validate new evaluation measures. Indeed, an evaluation measure that is highly correlated to the manual evaluation is appropriate for the evaluation of automatic keyphrase extraction methods.

In this paper, we present ISO-TimeML, a revised and interoperable version of the temporal markup language, TimeML. We describe the changes and enrichments made, while framing the effort in a more general methodology of semantic annotation. In particular, we assume a principled distinction between the annotation of an expression and the representation which that annotation denotes. This involves not only the specification of an annotation language for a particular phenomenon, but also the development of a meta-model that allows one to interpret the syntactic expressions of the specification semantically.

The fast evolution of language technology has produced pressing needs in standardization. The multiplicity of language resources representation levels and the specialization of these representations make difficult the interaction between linguistic resources and components manipulating these resources. In this paper, we describe the MultiLingual Information Framework (MLIF ― ISO CD 24616). MLIF is a metamodel which allows the representation and the exchange of multilingual textual information. This generic metamodel is designed to provide a common platform for all the tools developed around the existing multilingual data exchange formats. This platform provides, on the one hand, a set of generic data categories for various application domains, and on the other hand, strategies for the interoperability with existing standards. The objective is to reach a better convergence between heterogeneous standardisation activities that are taking place in the domain of data modeling (XML; W3C), text management (TEI; TEIC), multilingual information (TMX-LISA; XLIFF-OASIS) and multimedia (SMILText; W3C). This is a work in progress within ISO-TC37 in order to define a new ISO standard.

This paper describes an ISO project which aims at developing a standard for annotating spoken and multimodal dialogue with semantic information concerning the communicative functions of utterances, the kind of semantic content they address, and their relations with what was said and done earlier in the dialogue. The project, ISO 24617-2 ""Semantic annotation framework, Part 2: Dialogue acts"", is currently at DIS stage. The proposed annotation schema distinguishes 9 orthogonal dimensions, allowing each functional segment in dialogue to have a function in each of these dimensions, thus accounting for the multifunctionality that utterances in dialogue often have. A number of core communicative functions is defined in the form of ISO data categories, available at http://semantic-annotation.uvt.nl/dialogue-acts/iso-datcats.pdf; they are divided into ""dimension-specific"" functions, which can be used only in a particular dimension, such as Turn Accept in the Turn Management dimension, and ""general-purpose"" functions, which can be used in any dimension, such as Inform and Request. An XML-based annotation language, ""DiAML"" is defined, with an abstract syntax, a semantics, and a concrete syntax.

The development of a multilingual terminology is a very long and costly process. We present the creation of a multilingual terminological database called GRISP covering multiple technical and scientific fields from various open resources. A crucial aspect is the merging of the different resources which is based in our proposal on the definition of a sound conceptual model, different domain mapping and the use of structural constraints and machine learning techniques for controlling the fusion process. The result is a massive terminological database of several millions terms, concepts, semantic relations and definitions. The accuracy of the concept merging between several resources have been evaluated following several methods. This resource has allowed us to improve significantly the mean average precision of an information retrieval system applied to a large collection of multilingual and multidomain patent documents. New specialized terminologies, not specifically created for text processing applications, can be aggregated and merged to GRISP with minimal manual efforts.

Within the CLARIN e-science infrastructure project it is foreseen to develop a component-based registry for metadata for Language Resources and Language Technology. With this registry it is hoped to overcome the problems of the current available systems with respect to inflexible fixed schema, unsuitable terminology and interoperability problems. The registry will address interoperability needs by refering to a shared vocabulary registered in data category registries as they are suggested by ISO.

Central Ontologies are increasingly important to manage interoperability between different types of language resources. This was the reason for ISO to set up a new committee ISO TC37/SC4 taking care of language resource management issues. Central to the work of this committee is the definition of a framework for a central registry of data categories that are important in the domain of language resources. This paper describes an application programming interface that was designed to request services from this data category registry. The DCR is operational and the described API has already been tested from a lexicon application.

A number of serious reasons will convince an increasing amount of researchers to store their relevant material in centers which we will call "language resource archives". They combine the duty of taking care of long-term preservation as well as the task to give access to their material to different user groups. Access here is meant in the sense that an active interaction with the data will be made possible to support the integration of new data, new versions or commentaries of all sorts. Modern Language Resource Archives will have to adhere to a number of basic principles to fulfill all requirements and they will have to be involved in federations to create joint language resource domains making it even simpler for the researchers to access the data. This paper makes an attempt to formulate the essential pillars language resource archives have to adhere to.

Metadata descriptions of language resources become an increasing necessity since the shear amount of language resources is increasing rapidly and especially since we are now creating infrastuctures to access these resources via the web through integrated domains of language resource archives. Yet, the metadata frameworks offered for the domain of language resources (IMDI and OLAC), although mature, are not as widely accepted as necessary. The lack of confidence in the stability and persistence of the concepts and formats introduced by these metadata sets seems to be one argument for people to not invest the time needed for metadata creation. The introduction of these concepts into an ISO standardization process may convince contributors to make use of the terminology. The availability of the ISO Data Category Registry that includes a metadata profile will also offer the opportunity for researchers to construct their own metadata set tailored to the needs of the project at hand, but nevertheless supporting interoperability.

A Linguistic Annotation Framework (LAF) is being developed within the International Standards Organization Technical Committee 37 Sub-committee on Language Resource Management (ISO TC37 SC4). LAF is intended to provide a standardized means to represent linguistic data and its annotations that is defined broadly enough to accommodate all types of linguistic annotations, and at the same time provide means to represent precise and potentially complex linguistic information. The general principles informing the design of LAF have been previously reported (Ide and Romary, 2003; Ide and Romary, 2004a). This paper describes some of the more technical aspects of the LAF design that have been addressed in the process of finalizing the specifications for the standard.

In this paper, we present the first sizable grammar built for Vietnamese using LTAG, developed over the past two years, named vnLTAG. This grammar aims at modelling written language and is general enough to be both application- and domain-independent. It can be used for the morpho-syntactic tagging and syntactic parsing of Vietnamese texts, as well as text generation. We then present a robust parsing scheme using vnLTAG and a parser for the grammar. We finish with an evaluation using a test suite.

Les corpus français librement accessibles annotés à d’autres niveaux linguistiques que morpho-syntaxique sont insuffisants à la fois quantitativement et qualitativement. Partant de ce constat, la FREEBANK – construite sur la base d’outils d’analyse automatique dont la sortie est révisée manuellement – se veut une base de corpus du français annotés à plusieurs niveaux (structurel, morphologique, syntaxique, coréférentiel) et à différents degrés de finesse linguistique qui soit libre d’accès, codée selon des schémas normalisés, intégrant des ressources existantes et ouverte à l’enrichissement progressif.

An unified language for the communicative acts between agents is essential for the design of multi-agents architectures. Whatever the type of interaction (linguistic, multimodal, including particular aspects such as force feedback), whatever the type of application (command dialogue, request dialogue, database querying), the concepts are common and we need a generic meta-model. In order to tend towards task-independent systems, we need to clarify the modules parameterization procedures. In this paper, we focus on the characteristics of a meta-model designed to represent meaning in linguistic and multimodal applications. This meta-model is called MMIL for MultiModal Interface Language, and has first been specified in the framework of the IST MIAMM European project. What we want to test here is how relevant is MMIL for a completely different context (a different task, a different interaction type, a different linguistic domain). We detail the exploitation of MMIL in the framework of the IST OZONE European project, and we draw the conclusions on the role of MMIL in the parameterization of task-independent dialogue managers.

The aim of the MEDIA project is to design and test a methodology for the evaluat ion of context-dependent and independent spoken dialogue systems. We propose an evaluation paradigm based on the use of test suites from real-world corpora and a common semantic representation and common metrics. This paradigm should allow us to diagnose the context-sensitive understanding capability of dialogue system s. This paradigm will be used within an evaluation campaign involving several si tes all of which will carry out the task of querying information from a database .

Customization of Machine Translation (MT) is a prerequisite for corporations to adopt the technology. It is therefore important but nonetheless challenging. Ongoing implementation proves that XML is an excellent exchange device between MT modules that efficiently enables interaction between the user and the processes to reach highly granulated structure-based customization. Accomplished through an innovative approach called the SYSTRAN Translation Stylesheet, this method is coherent with the current evolution of the “authoring process”. As a natural progression, the next stage in the customization process is the integration of MT in a multilingual tool kit designed for the “authoring process”.