Open AccessQuand la réponse se trouve dans un grand corpus
Author(s) -
Olivier Ferret,
Brigitte Grau,
Martine Hurault-Plantet,
Gabriel Ilouz,
Christian Jacquemin
Publication year - 2002
Publication title -
ingénierie des systèmes d information
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.161
H-Index - 8
eISSN - 2116-7125
pISSN - 1633-1311
DOI - 10.3166/isi.7.1-2.95-123
Subject(s) - sentence , question answering , computer science , natural language processing , artificial intelligence , domain (mathematical analysis) , linguistics , information retrieval , humanities , philosophy , mathematics , mathematical analysis
Answering to open-domain factual questions requir es to apply Natural Language treatments to retrieved documents in order to be ab le to locate the answers inside them. We developed a system, QALC, that participated to the Question Answering track of the TREC8 and TREC9 evaluations. QALC exploits an analysis of documents based on the search for multi-words terms and their variations both to sele ct a minimal number of documents to be processed and to give indices when comparing questi on and sentence representations. This comparison also takes advantage of a question analy sis module and a recognition of named entities in the documents. MOTS-CLES. Systeme de question-reponse, extraction de terme, variante terminologique, entite nommee, recherche d'information
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom