Papers by Vincent Barbier
IJCAI Workshop on …, 2005
QA systems need semantic knowledge to find in documents variations of the question terms. They be... more QA systems need semantic knowledge to find in documents variations of the question terms. They benefit from the use of knowledge resources such as synonym dictionaries or ontologies like Word-Net. Our goal here is to study to which extent variations are needed and to determine what kinds of variations are useful or necessary for these systems. This study is based on different corpora in which we analyze semantic term variations, based on reference sets of possible variations.
In a question answering system, the first steps consist in retrieving documents relevant to the q... more In a question answering system, the first steps consist in retrieving documents relevant to the question, from which sentences are extracted. In these steps, the possible variations between the formulations of the question and the candidate sentences should be taken into account. The selection of documents has to be large enough to ensure a high recall, but the noise generated by the reformulations has to be contained. In this article, we will present a method for filtering and reranking the candidate sentences of the documents according to syntactic criteria.
A Corpus for Studying Full Answer Justification
Question answering (QA) systems aim at retrieving precise information from a large collection of ... more Question answering (QA) systems aim at retrieving precise information from a large collection of documents. To be considered as reliable by users, a QA system must provide elements to evaluate the answer. This notion of answer justification can also be useful when developping a QA system in order to give criteria for selecting correct answers. An answer justification can be found in a sentence, a passage made of several consecutive sentences or several passages of a document or several documents. Thus, we are interesting in pinpointing the set of information that allows to verify the correctness of the answer in a candidate passage and the question elements that are missing in this passage. Moreover, the relevant information is often given in texts in a different form from the question form: anaphora, paraphrases, synonyms. In order to have a better idea of the importance of all the phenomena we underlined, and to provide enough examples at the QA developer’s disposal to study them,...
Ce memoire se situe dans le domaine des systemes de questions-reponses, ces systemes qui, a parti... more Ce memoire se situe dans le domaine des systemes de questions-reponses, ces systemes qui, a partir d'une question en langage naturel posee par l'utilisateur recherche une reponse dans une collection de documents. Notre travail se fonde sur la notion de justification, que nous formalisons comme un graphe d'appariement entre les informations linguistiques extraites de la question et les elements justificatifs correspondants de le passage reponse. Ce modele fait intervenir trois types de phenomenes linguistiques : les variations paradigmatiques locales d'un terme (semantiques, morphologiques, inferences), les liens syntagmatiques entre les constituants d'une phrase, et une composante de semantique enonciative reliant des elements distants (anaphores, coreferences, thematisation), dans un contexte multiphrase, aussi bien mono- que multi-documents. Dans ce travail, nous decrivons premierement l'extraction semi-automatique d'un corpus de questions-reponses. Ce ...
Les systèmes de Questions Réponse ont besoin de connaissances sémantiques pour trouver dans les d... more Les systèmes de Questions Réponse ont besoin de connaissances sémantiques pour trouver dans les documents des termes susceptibles d’être des reformulations des termes de la question. Cependant, l’utilisation de ressources sémantiques peut apporter un bruit important et altérer la précision du système. ne fournit qu’une partie des reformulations possibles. Cet article présente un cadre d’évaluation pour les ressources sémantiques dans les systèmes de question-réponse. Il décrit la fabrication semi-automatique d’un corpus de questions et de réponses destiné à étudier les reformulations présentes entre termes de la question et termes de la réponse. Il étudie la fréquence et la fiabilité des reformulations extraites de l’ontologie WordNet.
Utilisation de connaissances sémantiques pour l’analyse de justifications de réponses à des questions
Http Www Theses Fr, 2009
A syntactic strategy for filtering sentences in a question answering system
In a question answering system, the first steps consist in retrieving documents relevant to the q... more In a question answering system, the first steps consist in retrieving documents relevant to the question, from which sentences are extracted. In these steps, the possible variations between the formulations of the question and the candidate sentences should be taken into account. The selection of documents has to be large enough to ensure a high recall, but the noise generated by the reformulations has to be contained. In this article, we will present a method for filtering and reranking the candidate sentences of the documents according to syntactic criteria.
Uploads
Papers by Vincent Barbier