This is an internal, incomplete preview of a proposed change to the ACL Anthology.
For efficiency reasons, we don't generate MODS or Endnote formats, and the preview may be incomplete in other ways, or contain mistakes.
Do not treat this content as an official publication.
KévinEspasa
Fixing paper assignments
Please select all papers that belong to the same person.
Indicate below which author they should be assigned to.
Lexical substitution task requires to substitute a target word by candidates in a given context. Candidates must keep meaning and grammatically of the sentence. The task, introduced in the SemEval 2007, has two objectives. The first objective is to find a list of substitutes for a target word. This list of substitutes can be obtained with lexical resources like WordNet or generated with a pre-trained language model. The second objective is to rank these substitutes using the context of the sentence. Most of the methods use vector space models or more recently embeddings to rank substitutes. Embedding methods use high contextualized representation. This representation can be over contextualized and in this way overlook good substitute candidates which are more similar on non-contextualized layers. SemDis 2014 introduced the lexical substitution task in French. We propose an application of the state-of-the-art method based on BERT in French and a novel method using contextualized and non-contextualized layers to increase the suggestion of words having a lower probability in a given context but that are more semantically similar. Experiments show our method increases the BERT based system on the OOT measure but decreases on the BEST measure in the SemDis 2014 benchmark.
La compression multi-phrases est utilisée dans différentes tâches de résumé (microblogs, opinions, réunions ou articles de presse). Leur objectif est de proposer une reformulation compressée et grammaticalement correcte des phrases sources tout en gardant les faits principaux. Dans cet article, nous présentons l’état de l’art de la compression multi-phrases en mettant en avant les différents corpus et outils à disposition. Nous axons notre analyse principalement sur la qualité grammaticale et informative plus que sur le taux de compression.
Depuis plusieurs années, Syllabs intègre de nombreux composants au sein d’un agréfilter, utilisant des technologies d’extraction d’information développées en interne et dans un contexte multilingue. Originellement conçu pour agréger des contenus issus de la presse, SylNews peut être utilisé à des fins de veille, pour explorer des contenus, ou pour identifier d’une manière plus globale les sujets chauds de l’ensemble ou d’une partie des contenus stockés.