A Question/Answer Typology with Surface Text Patterns
نویسندگان
چکیده
In this paper we announce the release of ISI’s QA Typology, which is being made available on the web to support the rapid construction of new QA systems. The Typology has been augmented with surface-level patterns associated with answer types, allowing systems to locate answers of the desired type in text by simple string matching. These patterns are extracted from the web automatically. We describe the process of their extraction, compression, and accuracy determination.
منابع مشابه
Using a Named Entity Tagger to Generalise Surface Matching Text Patterns for Question Answering
This paper explores one particular limitation common to question answering systems which operate by using induced surface matching text patterns – namely the problems concerned with question specific words appearing within the induced answer extraction pattern. We suggest a solution to this problem by generalising the learned answer extraction patterns to include named entity classes.
متن کاملAutomatic Derivation of Surface Text Patterns for a Maximum Entropy Based Question Answering System
In this paper we investigate the use of surface text patterns for a Maximum Entropy based Question Answering (QA) system. These text patterns are collected automatically in an unsupervised fashion using a collection of trivia question and answer pairs as seeds. These patterns are used to generate features for a statistical question answering system. We report our results on the TREC-10 question...
متن کاملA Text Mining Approach for Definition Question Answering
This paper describes a method for definition question answering based on the use of surface text patterns. The method is specially suited to answer questions about person’s positions and acronym’s descriptions. It considers two main steps. First, it applies a sequence-mining algorithm to discover a set of definition-related text patterns from the Web. Then, using these patterns, it extracts a c...
متن کاملILQUA at TREC 2006
This year, we made changes to the passage/sentence retrieval component of ILQUA in handling factoid and list questions. All the other components remain same. ILQUA is an IE-driven QA system. To answer “Factoid” and “List” questions, we apply our answer extraction methods on NE-tagged passages or sentences. The answer extraction methods adopted here are surface text pattern matching, n-gram prox...
متن کاملThe patterns and behaviors of researchers’ knowledge sharing in scientific social networks:A Case Study of Research Gate’ Question And Answer System
Aim: Scientific social networks were shaped as part of a set of social software and a platform for international interactions sharing the tangible and intangible knowledge of researchers. The purpose is to investigate the patterns and behaviors of knowledge sharing of researchers in Research Gate. Based on this, the question and answer system of this scientific social network was analyzed and r...
متن کامل