AnswerFinder in TREC 2003

نویسنده

  • Diego Mollá Aliod
چکیده

In this our first participation in TREC we have focused on the passage task of the question answering track. The main aim of our participation was to test the impact of various types of linguistic information in a simple question answering system. In particular, we have tested various combinations of word overlap, grammatical relations overlap, and overlap of minimal logical forms in the final scoring module of the system. The results indicate a small increase of accuracy with respect to a baseline system based on word overlap. Overall, given the short time available for developing the system, the results are satisfactory and equal or surpass the median.

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

AnswerFinder at TREC 2005

AnswerFinder has been completely redesigned for TREC 2005. The new architecture allows a fast development of question-answering systems for their deployment in the TREC tasks and other applications. The AnswerFinder modules use XML to express the services they provide, and they can be queried with XML for their services. The QA method now incorporates graphbased methods to compute the answerhoo...

متن کامل

AnswerFinder at TREC 2004

AnswerFinder combines lexical, syntactic, and semantic information in various stages of the question answering process. The candidate sentences are preselected on the basis of (i) the presence of named entity types compatible with the expected answer type, and (ii) a score combination of the overlap of words, grammatical relations, and flat logical forms. The candidate answers, in turn, are ext...

متن کامل

Answerfinder: Question Answering by Combining Lexical, Syntactic and Semantic Information

We present a question answering system that combines information at the lexical, syntactic, and semantic levels, in the process to find and rank the candidate answer sentences. The candidate exact answers are extracted from the candidate answer sentences by means of a combination of information-extraction techniques (named entity recognition) and patterns based on logical forms. The system part...

متن کامل

AnswerFinder: Question Answering from your Desktop

For many years Internet search engines have made a valiant attempt at quickly finding documents relevant to a users query. As the size of the Internet continues to grow, however, these search engines are returning more and more documents for a single query, leaving the user to wade through a vast amount of text. What is required are a new range of systems that are not only easy to use but are c...

متن کامل

Learning of Graph Rules for Question Answering

AnswerFinder is a framework for the development of question-answering systems. AnswerFinder is currently being used to test the applicability of graph representations for the detection and extraction of answers. In this paper we briefly describe AnswerFinder and introduce our method to learn graph patterns that link questions with their corresponding answers in arbitrary sentences. The method i...

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 2003