Abstract
We present a method for producing a bird's-eye view of statements that are expressed on Web pages on a given topic. This method aggregates statements that are relevant to the topic, and shows contradictory and contrastive relations among them. This view of contradictions and contrasts helps users acquire a top-down understanding of the topic. To realize this, we extract such statements and relations, including cross-document implicit contrastive relations between statements, in an unsupervised manner. Our experimental results indicate the effectiveness of our approach.
| Original language | English |
|---|---|
| Pages | 534-542 |
| Number of pages | 9 |
| Publication status | Published - Dec 1 2010 |
| Event | 23rd International Conference on Computational Linguistics, Coling 2010 - Beijing, China Duration: Aug 23 2010 → Aug 27 2010 |
Other
| Other | 23rd International Conference on Computational Linguistics, Coling 2010 |
|---|---|
| Country | China |
| City | Beijing |
| Period | 8/23/10 → 8/27/10 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Language and Linguistics
- Computational Theory and Mathematics
- Linguistics and Language
Cite this
Kawahara, D., Inui, K., & Kurohashi, S. (2010). Identifying contradictory and contrastive relations between statements to outline web information on a given topic. 534-542. Paper presented at 23rd International Conference on Computational Linguistics, Coling 2010, Beijing, China.