Ludovic Tanguy

Extensive data for morphology: using the World Wide Web

This paper presents a number of recent studies in French morphology which make extensive use of data. These data relating to derived words have been automatically collected from digital corpora, mostly from the Web. The main point developed here is that this massive increase in the amount of available data can substantially modify the results of a morphological study, and can lead to new theoretical conclusions that would not have been possible with traditional data such as wordlists gathered from dictionaries. However, using the Web as a corpus brings up several technical and methodological questions, which are dealt with through examples and discussions about the different tools and techniques available. We exemplify our thesis through the study of the suffixal forms: -esque ,- este ,- able ,- ment.

Integrating Multidisciplinary Results to Produce New Knowledge About the Physician–Patient Relationship A Methodology Applied to the INTERMEDE Project

The INTERMEDE Project brought together a number of research teams to study the interaction between a patient and their general practitioner, and how this can produce social inequalities in health. The ultimate objective of the project was to formalize a core of common findings by integrating qualitative and quantitative results. The methodology chosen for the integration was inspired by the Delphi participatory method. It involves several rounds of questions and feedback in writing between all members of project teams, in order to compare contradictory opinions and identify key concepts arising from the project. This interdisciplinary research has provided a more nuanced understanding of the mechanisms underlying physician–patient interaction by revealing the convergences of the various disciplinary approaches.

Citations in Scientific Texts: Do Social Relations Matter?

This article presents an investigation of the role of social relations in the writing of scientific articles through the study of in‐text citations. Does the fact that the author of an article knows the author whose work he or she cites have an impact on the context of the citation? Because citations are commonly used as criteria for research evaluation, it is important to question their social background to better understand how it impacts textual features. We studied a collection of science articles (N = 123) from 5 disciplines and interviewed their authors (N = 84) to: (a) identify the social relations between citing and cited authors; and (b) measure the correlation between a set of features related to in‐text citations (N = 6,956) and the identified social relations. Our pioneering work, mixing sociological and linguistic results, shows that social relations between authors can partly explain the variations of citations in terms of frequency, position and textual context.

IRIT-QFR: IRIT Query Feature Resource

In this paper, we present a resource that consists of query features associated with TREC adhoc collections. We developed two types of query features: linguistics features that can be calculated from the query itself, prior to any search although some are collection-dependent and post-retrieval features that imply the query has been evaluated over the target collection. This paper presents the two types of features that we have estimated as well as their variants, and the resource produced. The total number of features with their variants that we have estimated is 258 where the number of pre-retrieval and post-retrieval features are 81 and 171, respectively. We also present the first analysis of this data that shows that some features are more relevant than others in IR applications. Finally, we present a few applications in which these resources could be used although the idea of making them available is to foster new usages for IR.

Exploring Wikipedia talk pages for conflict detection

The present study concentrates on Wikipedia talk pages, which are online discussions where the authors discuss the composition and content of Wikipedia articles. These pages provide new data for describing and analysing collaborative writing processes, which often involve conflicts. Previously, many studies have explored Wikipedia conflicts, highlighting opposite editing patterns in relation to cooperation, conflicts or quality. Most of these studies belong to the field of social sciences, and linguistic analyses are not very common in this context. Therefore, the linguistic characteristics of Wikipedia conflicts in talk pages are still little described in the literature. In this context, our objective is to analyse relevant linguistic cues which may help identify and characterize conflicts on Wikipedia talk pages. To this end, we apply two automatic methods. The first consists of the supervised automatic classification of conflicting vs. harmonic discussion threads. Secondly, we apply multidimensional analysis to the data to help profile the Wikipedia talk genre, enabling us to highlight key features and oppositions at a global level. The analyses are carried out on the WikiTalk corpus, a resource based on the French Wikipedia talk pages (160M words, 3M posts, 1M threads). The corpus includes a wide range of metadata, providing extra-linguistic characterization of the Wikipedia discussions.

Découverte de configurations de traits textuels pour la caractérisation des segments d'obsolescence

Cet article presente une methodologie de decouverte de marqueurs envisages comme des configurations de traits textuels pour la description et le reperage automatique de segments contenant des informations necessitant des mises a jour (les segments d’obsolescence). La methodologie mise en œuvre est fondee sur la prise en compte de traits textuels heterogenes et a granularite variable. Nous mettons en place un systeme statistique a base de regles d’association pour faire emerger des donnees les combinaisons de traits pertinentes : traits intraphrastiques, hierarchiques, positionnels et externes. Une evaluation de leur role en termes de performance est proposee. Nous travaillons sur un corpus de textes encyclopediques annote manuellement par des redacteurs du monde de l’edition.