منابع مشابه
Répondre à des questions à réponses multiples : premières expérimentations
Question-answering systems have multiples problems dealing with answer extraction from retrieved documents, especially when cross-checking is needed for questions expecting multiple answers. We focused on answer extraction and answer crossing by building an ideal corpus for a dozen of multiple answer questions. We performed a fine-grained evaluation on each strategy for answer extraction and va...
متن کاملAbcès de l'avant bras: penser à l'ostéomyélite, même chez un adulte immunocompétent
L'ostéomyélite est classiquement décrite chez l'enfant. Elle est la conséquence de la contamination de l'os, par voie hématogène, par un ou plusieurs microorganismes. Elle affecte habituellement la métaphyse des os longs des membres inférieurs. L'affection est rarement rapportée au-delà de 18 ans. Quand elle survient chez l'adulte, le plus souvent elle fait suite à une contamination directe pos...
متن کامل...Plus la Même Chose
In the last editorial (‘plus ça change’—[1]), we briefly looked at some of the major changes in scholarly communication, and how some things hadn’t changed at all. This lack of change has frustrated all of those progressives who feel we’ve not even begun to take advantage of all the opportunities offered. It’s easy to sympathise, when you think of all the things we can now do with electronic sy...
متن کاملRépondre à des questions à réponses multiples sur le Web. (Answering multiple answer questions from the Web)
Question answering systems find and extract a precise answer to a question in natural language. Both current question-answering systems and evaluation campaigns often assume that only one single answer is expected for a question. Our corpus studies show that this is rarely the case, specially when answers are extracted from the Web instead of a frozen collection of documents. We therefore focus...
متن کاملApprentissage d'inférences par édition d'arbres pour répondre à des questions
In order to answer question, we propose a matching algorithm that consists in generating and learning inferences needed to rely text passages to pairs (question, candidate answer). We first retrieve relevant passages, through lexical expansion involving WordNet and word vectors, that are enriches by lexico-semantic resources. Then a tree edit model is used on graph representations of the passag...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Critique d’art
سال: 2014
ISSN: 1246-8258,2265-9404
DOI: 10.4000/critiquedart.13548