Extrans, an Answer Extraction System

نویسندگان

  • Diego MOLLÁ
  • Rolf SCHWITTER
  • Michael HESS
  • Rachel FOURNIER
چکیده

Les systèmes d’Extraction de Réponses (ER) récupèrent dans des documents des expressions qui répondent directement à des questions du langage courant. L’ER pour des manuels techniques exige un haut niveau de rappel et de précision ; pourtant, ce sont de petites unités de texte qui doivent être récupérées. C’est pourquoi il est important d’effectuer une analyse linguistique détaillée. Nous présentons ici ExtrAns, un système d’ER pour des manuels Unix qui utilise une analyse syntaxique complète, une désambiguïsation partielle et un module de résolution d’anaphores pour générer les formes logiques minimales correspondant aux documents et à la requête. La procédure de recherche se sert d’un algorithme de démonstration de la requête sur la représentation en clauses de Horn des formes logiques minimales. Les ambiguïtés non résolues sont traitées à l’aide d’une mise en évidence graduelle.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Dependency-Based Semantic Interpretation for Answer Extraction

This paper focuses on the use of two algorithms for the integration of two broad-coverage dependency-based parsing systems into ExtrAns, an answer extraction system that operates over Unix manual pages. In the process, ExtrAns uses a semantic interpreter that converts the output of the parser into flat logical forms. The semantic interpreter for the first parsing system, Link Grammar, uses a to...

متن کامل

ExtrAns Answer Extraction from Technical Documents by Minimal Logical Forms and Selective Highlighting

Logic-based answer extraction techniques present a solution to retrieve and mark those exact passages in a document that directly answer a natural language query. In contrast to pure information retrieval techniques that treat content words as isolated terms, answer extraction techniques exploit syntactic information in a document to a certain degree and consider semantic relations between func...

متن کامل

A Real World Implementation of Answer Extraction

In this paper we describe ExtrAns, an answer extraction system. Answer extraction (AE) aims at retrieving those exact passages of a document that directly answer a given user question. AE is more ambitious than information retrieval and information extraction in that the retrieval results are phrases, not entire documents, and in that the queries may be arbitrarily specific. It is less ambitiou...

متن کامل

From Minimal Logical Forms for Answer Extraction to Logical Graphs for Question Answering

Many exciting things happened since I left the ExtrAns project at the University of Zurich. In this paper I present a very brief journal of the research that derived from my work at Zurich. My work combined a study of several representations of questions and answer sentences with the development of procedures to find the answer. The culmination of this work was the definition of the Logical Gra...

متن کامل

Towards Answer Extraction: An application to Technical Domains

The shortcomings of traditional Information Retrieval are most evident when users require exact information rather than relevant documents. This practical need is pushing the research community towards systems that can exactly pinpoint those parts of documents that contain the information requested. Answer Extraction (AE) systems aim to satisfy this need. This paper presents one such system (Ex...

متن کامل

Answer Extraction Using a Dependency Grammar in Extrans

Nous exposons ici l’implémentation d’un système d’extraction de réponses, ExtrAns, qui utilise la sortie d’un analyseur et d’une grammaire basés sur les dépendances. Afin d’augmenter la vitesse de calcul, l’analyseur et la grammaire utilisés sacrifient le fonctionnalisme (dans le cadre des grammaires de dépendance) au profit de la projectivité. Nous avons découvert que les structures de dépenda...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2000