Advanced

Exploring Lexicalized Features for Coreference Resolution

Björkelund, Anders and Nugues, Pierre LU (2011) The 15th Conference on Computational Natural Language Learning (CoNLL-2011): Shared Task In [Host publication title missing] p.45-50
Abstract
In this paper, we describe a coreference solver based on the extensive use of lexical features and features extracted from dependency graphs of the sentences. The solver uses Soon et al. (2001)'s classical resolution algorithm based on a pairwise classification of the mentions.



We applied this solver to the closed track of the CoNLL 2011 shared task (Pradhan et al., 2011). We carried out a systematic optimization of the feature set using cross-validation that led us to retain 24 features. Using this set, we reached a MUC score of 58.61 on the test set of the shared task. We analyzed the impact of the features on the development set and we show the importance of lexicalization as well as of properties related to... (More)
In this paper, we describe a coreference solver based on the extensive use of lexical features and features extracted from dependency graphs of the sentences. The solver uses Soon et al. (2001)'s classical resolution algorithm based on a pairwise classification of the mentions.



We applied this solver to the closed track of the CoNLL 2011 shared task (Pradhan et al., 2011). We carried out a systematic optimization of the feature set using cross-validation that led us to retain 24 features. Using this set, we reached a MUC score of 58.61 on the test set of the shared task. We analyzed the impact of the features on the development set and we show the importance of lexicalization as well as of properties related to dependency links in coreference resolution. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
in
[Host publication title missing]
pages
45 - 50
conference name
The 15th Conference on Computational Natural Language Learning (CoNLL-2011): Shared Task
ISBN
9781937284084
language
English
LU publication?
yes
id
4bbfa11d-e166-47c2-b1a2-0d3946e2e2c6 (old id 2972016)
date added to LUP
2012-08-17 10:27:58
date last changed
2016-04-16 11:17:56
@misc{4bbfa11d-e166-47c2-b1a2-0d3946e2e2c6,
  abstract     = {In this paper, we describe a coreference solver based on the extensive use of lexical features and features extracted from dependency graphs of the sentences. The solver uses Soon et al. (2001)'s classical resolution algorithm based on a pairwise classification of the mentions.<br/><br>
<br/><br>
We applied this solver to the closed track of the CoNLL 2011 shared task (Pradhan et al., 2011). We carried out a systematic optimization of the feature set using cross-validation that led us to retain 24 features. Using this set, we reached a MUC score of 58.61 on the test set of the shared task. We analyzed the impact of the features on the development set and we show the importance of lexicalization as well as of properties related to dependency links in coreference resolution.},
  author       = {Björkelund, Anders and Nugues, Pierre},
  isbn         = {9781937284084},
  language     = {eng},
  pages        = {45--50},
  series       = {[Host publication title missing]},
  title        = {Exploring Lexicalized Features for Coreference Resolution},
  year         = {2011},
}