Search Results for author:
Found 12 papers, 1 papers with code
Investigating associative, switchable and negatable Winograd items on renewed French data sets
The Winograd Schema Challenge (WSC) consists of a set of anaphora resolution problems resolvable only by reasoning about world knowledge.
How to Evaluate Coreference in Literary Texts?
In this short paper, we examine the main metrics used to evaluate textual coreference and we detail some of their limitations.
VerNom : une base de paires morphologiques acquise sur tr\`es gros corpus (VerNom : a French derivational database acquired on a massive corpus)
Alors qu{'}une part active de la recherche en morphologie d{\'e}rivationnelle s{'}int{\'e}resse {\`a} la comp{\'e}tition qui oppose les suffixations construisant des noms d{'}{\'e}v{\'e}nement {\`a} partir de verbes (-age, -ment, -ion, -ure, -ance, -ade, -aison), l{'}acc{\`e}s {\`a} des donn{\'e}es en large quantit{\'e} devient n{\'e}cessaire pour l{'}application de m{\'e}thodes quantitatives.
Mod\`eles de langue appliqu\'es aux sch\'emas Winograd fran\ccais (Language Models applied to French Winograd Schemas)
Les performances que nous obtenons, surtout compar{\'e}es {\`a} celles de Amsili {\&} Seminck (2017b), sugg{\`e}rent que l{'}approche par mod{\`e}le de langue des sch{\'e}mas Winograd reste limit{\'e}e, sans doute en partie {\`a} cause du fait que les mod{\`e}les de langue encodent tr{\`e}s difficilement le genre de raisonnement n{\'e}cessaire {\`a} la r{\'e}solution des sch{\'e}mas Winograd.
R\'esolution des cor\'ef\'erences neuronale : une approche bas\'ee sur les t\^etes (Neural coreference resolution : a head-based approach)
L{'}av{\`e}nement des approches neuronales de bout en bout a entra{\^\i}n{\'e} une rupture dans la fa{\c{c}}on dont {\'e}tait jusqu{'}{\`a} pr{\'e}sent envisag{\'e}e et impl{\'e}ment{\'e}e la t{\^a}che de r{\'e}solution des cor{\'e}f{\'e}rences.
Sch\'emas Winograd en fran\ccais: une \'etude statistique et comportementale (Winograd schemas in French : a statistical and behavioral study)
Nous pr{\'e}sentons dans cet article une collection de sch{\'e}mas Winograd en fran{\c{c}}ais, adapt{\'e}e de la liste propos{\'e}e par Levesque et al. (2012) pour l{'}anglais.
A Google-Proof Collection of French Winograd Schemas
This article presents the first collection of French Winograd Schemas.
A Computational Model of Human Preferences for Pronoun Resolution
We present a cognitive computational model of pronoun resolution that reproduces the human interpretation preferences of the Subject Assignment Strategy and the Parallel Function Strategy.
Developing a French FrameNet: Methodology and First results
The Asfalda project aims to develop a French corpus with frame-based semantic annotations and automatic tools for shallow semantic analysis.
French TimeBank: An ISO-TimeML Annotated Reference Corpus
This article presents the main points in the creation of the French TimeBank (Bittar, 2010), a reference corpus annotated according to the ISO-TimeML standard for temporal annotation.
