Searcharxiv⌕ Search

arXiv subjects

Thierry Poibeau

Publications and source records attributed to Thierry Poibeau.

At least 37 records · Page 2Linked to original sources
arXiv2022

Does BERT really agree ? Fine-grained Analysis of Lexical Dependence on a Syntactic Task

Although transformer-based Neural Language Models demonstrate impressive performance on a variety of tasks, their generalization abilities are not well understood. They have been shown to perform strongly on subject-verb number agreement in a wide array of settings, suggesting that they learned to track syntactic dependencies during their training even without explicit supervision. In this paper, we examine the extent to which BERT is able to perform lexically-independent subject-verb number agreement (NA) on targeted syntactic templates. To do so, we disrupt the lexical patterns found in naturally occurring stimuli for each targeted structure in a novel fine-grained analysis of BERT's behavior. Our results on nonce sentences suggest that the model generalizes well for simple templates, but fails to perform lexically-independent syntactic generalization when as little as one attractor is present.

cs.CL↗
arXiv2020

Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing

Linguistic typology aims to capture structural and semantic variation across the world's languages. A large-scale typology could provide excellent guidance for multilingual Natural Language Processing (NLP), particularly for languages that suffer from the lack of human labeled resources. We present an extensive literature survey on the use of typological information in the development of NLP techniques. Our survey demonstrates that to date, the use of information in existing typological databases has resulted in consistent but modest improvements in system performance. We show that this is due to both intrinsic limitations of databases (in terms of coverage and feature granularity) and under-employment of the typological features included in them. We advocate for a new approach that adapts the broad and discrete nature of typological categories to the contextual and continuous nature of machine learning algorithms used in contemporary NLP. In particular, we suggest that such approach could be facilitated by recent developments in data-driven induction of typological knowledge.

cs.CL↗
arXiv2020

Automatic Dialect Adaptation in Finnish and its Effect on Perceived Creativity

We present a novel approach for adapting text written in standard Finnish to different dialects. We experiment with character level NMT models both by using a multi-dialectal and transfer learning approaches. The models are tested with over 20 different dialects. The results seem to favor transfer learning, although not strongly over the multi-dialectal approach. We study the influence dialectal adaptation has on perceived creativity of computer generated poetry. Our results suggest that the more the dialect deviates from the standard Finnish, the lower scores people tend to give on an existing evaluation metric. However, on a word association test, people associate creativity and originality more with dialect and fluency more with standard Finnish.

cs.CL↗
arXiv2020

Multi-SimLex: A Large-Scale Evaluation of Multilingual and Cross-Lingual Lexical Semantic Similarity

We introduce Multi-SimLex, a large-scale lexical resource and evaluation benchmark covering datasets for 12 typologically diverse languages, including major languages (e.g., Mandarin Chinese, Spanish, Russian) as well as less-resourced ones (e.g., Welsh, Kiswahili). Each language dataset is annotated for the lexical relation of semantic similarity and contains 1,888 semantically aligned concept pairs, providing a representative coverage of word classes (nouns, verbs, adjectives, adverbs), frequency ranks, similarity intervals, lexical fields, and concreteness levels. Additionally, owing to the alignment of concepts across languages, we provide a suite of 66 cross-lingual semantic similarity datasets. Due to its extensive size and language coverage, Multi-SimLex provides entirely novel opportunities for experimental evaluation and analysis. On its monolingual and cross-lingual benchmarks, we evaluate and analyze a wide array of recent state-of-the-art monolingual and cross-lingual representation models, including static and contextualized word embeddings (such as fastText, M-BERT and XLM), externally informed lexical representations, as well as fully unsupervised and (weakly) supervised cross-lingual word embeddings. We also present a step-by-step dataset creation protocol for creating consistent, Multi-Simlex-style resources for additional languages. We make these contributions -- the public release of Multi-SimLex datasets, their creation protocol, strong baseline results, and in-depth analyses which can be be helpful in guiding future developments in multilingual lexical semantics and representation learning -- available via a website which will encourage community effort in further expansion of Multi-Simlex to many more languages. Such a large-scale semantic resource could inspire significant further advances in NLP across languages.

cs.CL↗
arXiv2016

Introduction: Cognitive Issues in Natural Language Processing

This special issue is dedicated to get a better picture of the relationships between computational linguistics and cognitive science. It specifically raises two questions: "what is the potential contribution of computational language modeling to cognitive science?" and conversely: "what is the influence of cognitive science in contemporary computational linguistics?"

cs.CL↗
arXiv2015

Generating Navigable Semantic Maps from Social Sciences Corpora

It is now commonplace to observe that we are facing a deluge of online information. Researchers have of course long acknowledged the potential value of this information since digital traces make it possible to directly observe, describe and analyze social facts, and above all the co-evolution of ideas and communities over time. However, most online information is expressed through text, which means it is not directly usable by machines, since computers require structured, organized and typed information in order to be able to manipulate it. Our goal is thus twofold: 1. Provide new natural language processing techniques aiming at automatically extracting relevant information from texts, especially in the context of social sciences, and connect these pieces of information so as to obtain relevant socio-semantic networks; 2. Provide new ways of exploring these socio-semantic networks, thanks to tools allowing one to dynamically navigate these networks, de-construct and re-construct them interactively, from different points of view following the needs expressed by domain experts.

cs.CL↗
arXiv2015

Archaeology in the Digital Age: From Paper to Databases

Research units in archaeology often manage large and precious archives containing various documents, including reports on fieldwork, scholarly studies and reference books. These archives are of course invaluable, recording decades of work, but are generally hard to consult and access. In this context, digitizing full text documents is not enough: information must be formalized, structured and easy to access thanks to friendly user interfaces.

cs.DL↗
arXiv2014

Mapping the Economic Crisis: Some Preliminary Investigations

In this paper we describe our contribution to the PoliInformatics 2014 Challenge on the 2007-2008 financial crisis. We propose a state of the art technique to extract information from texts and provide different representations, giving first a static overview of the domain and then a dynamic representation of its main evolutions. We show that this strategy provides a practical solution to some recent theories in social sciences that are facing a lack of methods and tools to automatically extract information from natural language texts.

cs.CL↗
arXiv2014

Optimality Theory as a Framework for Lexical Acquisition

This paper re-investigates a lexical acquisition system initially developed for French.We show that, interestingly, the architecture of the system reproduces and implements the main components of Optimality Theory. However, we formulate the hypothesis that some of its limitations are mainly due to a poor representation of the constraints used. Finally, we show how a better representation of the constraints used would yield better results.

cs.CL↗
arXiv2013

Multi-Level Modeling of Quotation Families Morphogenesis

This paper investigates cultural dynamics in social media by examining the proliferation and diversification of clearly-cut pieces of content: quoted texts. In line with the pioneering work of Leskovec et al. and Simmons et al. on memes dynamics we investigate in deep the transformations that quotations published online undergo during their diffusion. We deliberately put aside the structure of the social network as well as the dynamical patterns pertaining to the diffusion process to focus on the way quotations are changed, how often they are modified and how these changes shape more or less diverse families and sub-families of quotations. Following a biological metaphor, we try to understand in which way mutations can transform quotations at different scales and how mutation rates depend on various properties of the quotations.

cs.CY↗
arXiv2008

Analyse et structuration automatique des guides de bonnes pratiques cliniques : essai d'évaluation

Health Practice Guideliens are supposed to unify practices and propose recommendations to physicians. This paper describes GemFrame, a system capable of semi-automatically filling an XML template from free texts in the clinical domain. The XML template includes semantic information not explicitly encoded in the text (pairs of conditions and ac-tions/recommendations). Therefore, there is a need to compute the exact scope of condi-tions over text sequences expressing the re-quired actions. We present a system developped for this task. We show that it yields good performance when applied to the analysis of French practice guidelines. We conclude with a precise evaluation of the tool.

cs.AI↗
arXiv2007

A Robust Linguistic Platform for Efficient and Domain specific Web Content Analysis

Web semantic access in specific domains calls for specialized search engines with enhanced semantic querying and indexing capacities, which pertain both to information retrieval (IR) and to information extraction (IE). A rich linguistic analysis is required either to identify the relevant semantic units to index and weight them according to linguistic specific statistical distribution, or as the basis of an information extraction process. Recent developments make Natural Language Processing (NLP) techniques reliable enough to process large collections of documents and to enrich them with semantic annotations. This paper focuses on the design and the development of a text processing platform, Ogmios, which has been developed in the ALVIS project. The Ogmios platform exploits existing NLP modules and resources, which may be tuned to specific domains and produces linguistically annotated documents. We show how the three constraints of genericity, domain semantic awareness and performance can be handled all together.

cs.AI↗
arXiv2007

Automatically Restructuring Practice Guidelines using the GEM DTD

This paper describes a system capable of semi-automatically filling an XML template from free texts in the clinical domain (practice guidelines). The XML template includes semantic information not explicitly encoded in the text (pairs of conditions and actions/recommendations). Therefore, there is a need to compute the exact scope of conditions over text sequences expressing the required actions. We present a system developed for this task. We show that it yields good performance when applied to the analysis of French practice guidelines.

cs.AI↗
arXiv2006

Event-based Information Extraction for the biomedical domain: the Caderige project

This paper gives an overview of the Caderige project. This project involves teams from different areas (biology, machine learning, natural language processing) in order to develop high-level analysis tools for extracting structured information from biological bibliographical databases, especially Medline. The paper gives an overview of the approach and compares it to the state of the art.

cs.AI↗
arXiv2006

Dealing with Metonymic Readings of Named Entities

The aim of this paper is to propose a method for tagging named entities (NE), using natural language processing techniques. Beyond their literal meaning, named entities are frequently subject to metonymy. We show the limits of current NE type hierarchies and detail a new proposal aiming at dynamically capturing the semantics of entities in context. This model can analyze complex linguistic phenomena like metonymy, which are known to be difficult for natural language processing but crucial for most applications. We present an implementation and some test using the French ESTER corpus and give significant results.

cs.AI↗
arXiv2006

Linguistically Grounded Models of Language Change

Questions related to the evolution of language have recently known an impressive increase of interest (Briscoe, 2002). This short paper aims at questioning the scientific status of these models and their relations to attested data. We show that one cannot directly model non-linguistic factors (exogenous factors) even if they play a crucial role in language evolution. We then examine the relation between linguistic models and attested language data, as well as their contribution to cognitive linguistics.

cs.AI↗
arXiv2005

Sur le statut référentiel des entités nommées

We show in this paper that, on the one hand, named entities can be designated using different denominations and that, on the second hand, names denoting named entities are polysemous. The analysis cannot be limited to reference resolution but should take into account naming strategies, which are mainly based on two linguistic operations: synecdoche and metonymy. Lastly, we present a model that explicitly represents the different denominations in discourse, unifying the way to represent linguistic knowledge and world knowledge.

cs.AI↗