Improving Name Tagging by Reference Resolution and Relation Detection (2005)
| Venue: | Proc. ACL2005 |
| Citations: | 13 - 8 self |
BibTeX
@INPROCEEDINGS{Ji05improvingname,
author = {Heng Ji and Ralph Grishman},
title = {Improving Name Tagging by Reference Resolution and Relation Detection},
booktitle = {Proc. ACL2005},
year = {2005},
pages = {411--418},
publisher = {Ann Arbor}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Information extraction systems incorporate multiple stages of linguistic analysis. Although errors are typically compounded from stage to stage, it is possible to reduce the errors in one stage by harnessing the results of the other stages. We demonstrate this by using the results of coreference analysis and relation extraction to reduce the errors produced by a Chinese name tagger. We use an N-best approach to generate multiple hypotheses and have them re-ranked by subsequent stages of processing. We obtained thereby a reduction of 24 % in spurious and incorrect name tags, and a reduction of 14 % in missed tags. 1
Citations
| 238 | Nymble: a High-Performance Learning Name-finder - Bikel, Miller, et al. - 1997 |
| 115 | A Maximum Entropy Approach to Named Entity Recognition - Borthwick - 1999 |
| 44 | The N-Best Algorithm: An Efficient Procedure for Finding Top N Sentence Hypotheses - Chow, Schwartz - 1989 |
| 21 | Active Hidden Markov Models for Information Extraction - Scheffer, Decomain, et al. - 2001 |
| 9 | Applying Coreference to Improve Name Recognition - Ji, Grishman - 2004 |
| 8 | Using N-best lists for named entity recognition from chinese speech - Zhai, Fung, et al. - 2004 |
| 5 | Chieu and Hwee Tou Ng. 2002. Named Entity Recognition: A Maximum Entropy Approach Using Global Information - Leong |
| 1 | Integer Programming for Information Extraction - Binary - 2004 |
