Abstract
Previous approaches to question retrieval in communitybased question answering rely on statistical translation techniques to match users' questions (queries) against collections of previously asked questions. This paper presents a simple but effective method for computing word relatedness to improve question retrieval based on word co-occurrence information directly extracted from question and answer archives. Experimental results show that the proposed approach significantly outperforms translation-based approaches.
| Original language | English |
|---|---|
| Pages (from-to) | 736-739 |
| Number of pages | 4 |
| Journal | IEICE Transactions on Information and Systems |
| Volume | E92-D |
| Issue number | 4 |
| DOIs | |
| Publication status | Published - 2009 Jan 1 |
Keywords
- Community question answering
- Question retrieval
- Word semantic relatedness
ASJC Scopus subject areas
- Software
- Hardware and Architecture
- Computer Vision and Pattern Recognition
- Electrical and Electronic Engineering
- Artificial Intelligence
Fingerprint Dive into the research topics of 'Computing word semantic relatedness for question retrieval in community question answering'. Together they form a unique fingerprint.
Cite this
Lee, J. T., Song, Y. I., & Rim, H. C. (2009). Computing word semantic relatedness for question retrieval in community question answering. IEICE Transactions on Information and Systems, E92-D(4), 736-739. https://doi.org/10.1587/transinf.E92.D.736