Getting answers to natural language questions on the Web
- 31 January 2002
- journal article
- research article
- Published by Wiley in Journal of the American Society for Information Science and Technology
- Vol. 53 (5) , 359-364
- https://doi.org/10.1002/asi.10053
Abstract
Most popular search engines are not designed for answering natural language questions. However, when we asked hundreds of natural language questions of nine leading search engines, all retrieved at least one correct answer on more than three‐quarters of the questions. We identified the best‐performing search engines overall for factual natural language questions. We found performance differences depending on the domain of factual question asked. Other aspects of questions also predicted significantly different performance: the number of words in the question, the presence of a proper noun, and whether the question is time dependent. An additional analysis tested for differential performance by specific search engines on these four question factors. The analysis found no evidence for such interactions.Keywords
This publication has 6 references indexed in Scilit:
- Question answering in TRECPublished by Association for Computing Machinery (ACM) ,2001
- Mining the web for answers to natural language questionsPublished by Association for Computing Machinery (ACM) ,2001
- Large scale testing of a descriptive phrase finderPublished by Association for Computational Linguistics (ACL) ,2001
- Question-answering by predictive annotationPublished by Association for Computing Machinery (ACM) ,2000
- Searching the World Wide WebScience, 1998
- Automated Information RetrievalLibrary and Information Science, 1997