Abstract
Integrating information from different stages of an NLP processing pipeline can yield significant error reduction. We demonstrate how re-ranking can improve name tagging in a Chinese information extraction system by incorporating information from relation extraction, event extraction, and coreference. We evaluate three state-of-the-art re-ranking algorithms (MaxEnt-Rank, SVMRank, and p-Norm Push Ranking), and show the benefit of multi-stage re-ranking for cross-sentence and cross-document inference.
| Original language | English (US) |
|---|---|
| Pages | 49-56 |
| Number of pages | 8 |
| State | Published - 2006 |
| Externally published | Yes |
| Event | 2006 Workshop on Computationally Hard Problems and Joint Inference in Speech and Language Processing - New York City, United States Duration: Jun 9 2006 → … |
Conference
| Conference | 2006 Workshop on Computationally Hard Problems and Joint Inference in Speech and Language Processing |
|---|---|
| Country/Territory | United States |
| City | New York City |
| Period | 6/9/06 → … |
ASJC Scopus subject areas
- Language and Linguistics
- Computational Theory and Mathematics
- Software
- Linguistics and Language