Filtering Out Bad Answers with Semantic Relations in a Web-Based Question-Answering System
نویسندگان
چکیده
De plus en plus de systèmes de question-réponses (QR) utilisent le Web pour trouver une réponse courte et précise à une question exprimée en langue naturelle. Dans cet article, nous présentons une méthode pour filtrer les mauvais candidats de réponses et re-ordonner les candidats dans notre module de QR en utilisant des relations sémantiques. L’idée est d’identifier la relation sémantique et l’argument principal exprimé dans la question et de trouver dans la collection de documents (ou sur le Web) d’autres indices indiquant que la relation sémantique entre l’argument de la question et le candidat de réponse existe vraiment. Les résultats avec le corpus de questions de TREC-9 et TREC-10 indique une nette amélioration de la précision de la liste des candidats.
منابع مشابه
Use of Semantic Similarity and Web Usage Mining to Alleviate the Drawbacks of User-Based Collaborative Filtering Recommender Systems
One of the most famous methods for recommendation is user-based Collaborative Filtering (CF). This system compares active user’s items rating with historical rating records of other users to find similar users and recommending items which seems interesting to these similar users and have not been rated by the active user. As a way of computing recommendations, the ultimate goal of the user-ba...
متن کاملAutomatic Acquisition of Semantic-Based Question Reformulations for Question Answering
In this paper, we present a method for the automatic acquisition of semantic-based reformulations from natural language questions. Our goal is to find useful and generic reformulation patterns, which can be used in our question answering system to find better candidate answers. We used 1343 examples of different types of questions and their corresponding answers from the TREC-8, TREC-9 and TREC...
متن کاملA Hybrid Filtering Approach for Question Answering
We describe a question answering system that took part in the bilingual CLEFQA task (German-English) where German is the source language and English the target language. We used the BableFish online translation system to translate the German questions into English. The system is targeted at Factoid and Definition questions. Our focus in designing the current system is on testing our online meth...
متن کاملUsing Generalized Language Model for Question Matching
Question and answering service is one of the popular services in the World Wide Web. The main goal of these services is to finding the best answer for user's input question as quick as possible. In order to achieve this aim, most of these use new techniques foe question matching. . We have a lot of question and answering services in Persian web, so it seems that developing a question matching m...
متن کاملCombining Resources to Find Answers to Biomedical Questions
One of the NLM experimental approaches to the 2007 Genomics track question answering task followed the track evaluation design: we attempted identifying exact answers in the form of semantic relations between biomedical entities named in questions and the potential answer types and then marked the passages containing the relations as containing the answers. The goal of this knowledgebased appro...
متن کامل