Bridging the lexical chasm
- 1 July 2000
- proceedings article
- Published by Association for Computing Machinery (ACM)
- p. 192-199
- https://doi.org/10.1145/345508.345576
Abstract
This paper investigates whether a machine can automatically learn the task of finding, within a large collection of candidate responses, the answers to questions. The learning process consists of inspecting a collection of answered questions and characterizing the relation between question and answer with a statistical model. For the purpose of learning this relation, we propose two sources of data: Usenet FAQ documents and customer service call-center dialogues from a large retail company. We will show that the task of “answer-finding” differs from both document retrieval and tradition question-answering, presenting challenges different from those found in these problems. The central aim of this work is to discover, through theoretical and empirical investigation, those statistical techniques best suited to the answer-finding problem.Keywords
This publication has 5 references indexed in Scilit:
- Probabilistic latent semantic indexingPublished by Association for Computing Machinery (ACM) ,1999
- Information retrieval as statistical translationPublished by Association for Computing Machinery (ACM) ,1999
- Query expansion using local and global document analysisPublished by Association for Computing Machinery (ACM) ,1996
- Indexing by latent semantic analysisJournal of the American Society for Information Science, 1990
- Term-weighting approaches in automatic text retrievalInformation Processing & Management, 1988