Zero-Anaphora Resolution in Chinese Using Maximum Entropy

Jing PENG; Kenji ARAKI

doi:10.1093/ietisy/e90-d.7.1092

Zero-Anaphora Resolution in Chinese Using Maximum Entropy

Jing PENG, Kenji ARAKI

Full Text Views

0

Share
Cite this

Summary :

In this paper, we propose a learning classifier based on maximum entropy (ME) for resolving zero-anaphora in Chinese text. Besides regular grammatical, lexical, positional and semantic features motivated by previous research on anaphora resolution, we develop two innovative Web-based features for extracting additional semantic information from the Web. The values of the two features can be obtained easily by querying the Web using some patterns. Our study shows that our machine learning approach is able to achieve an accuracy comparable to that of state-of-the-art systems. The Web as a knowledge source can be incorporated effectively into the ME learning framework and significantly improves the performance of our approach.

Publication: IEICE TRANSACTIONS on Information Vol.E90-D No.7 pp.1092-1102

Publication Date: 2007/07/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1093/ietisy/e90-d.7.1092

Type of Manuscript: PAPER

Category: Natural Language Processing

Cite this

Copy

Jing PENG, Kenji ARAKI, "Zero-Anaphora Resolution in Chinese Using Maximum Entropy" in IEICE TRANSACTIONS on Information, vol. E90-D, no. 7, pp. 1092-1102, July 2007, doi: 10.1093/ietisy/e90-d.7.1092.
Abstract: In this paper, we propose a learning classifier based on maximum entropy (ME) for resolving zero-anaphora in Chinese text. Besides regular grammatical, lexical, positional and semantic features motivated by previous research on anaphora resolution, we develop two innovative Web-based features for extracting additional semantic information from the Web. The values of the two features can be obtained easily by querying the Web using some patterns. Our study shows that our machine learning approach is able to achieve an accuracy comparable to that of state-of-the-art systems. The Web as a knowledge source can be incorporated effectively into the ME learning framework and significantly improves the performance of our approach.
URL: https://globals.ieice.org/en_transactions/information/10.1093/ietisy/e90-d.7.1092/_p

Copy

@ARTICLE{e90-d_7_1092,
author={Jing PENG, Kenji ARAKI, },
journal={IEICE TRANSACTIONS on Information},
title={Zero-Anaphora Resolution in Chinese Using Maximum Entropy},
year={2007},
volume={E90-D},
number={7},
pages={1092-1102},
abstract={In this paper, we propose a learning classifier based on maximum entropy (ME) for resolving zero-anaphora in Chinese text. Besides regular grammatical, lexical, positional and semantic features motivated by previous research on anaphora resolution, we develop two innovative Web-based features for extracting additional semantic information from the Web. The values of the two features can be obtained easily by querying the Web using some patterns. Our study shows that our machine learning approach is able to achieve an accuracy comparable to that of state-of-the-art systems. The Web as a knowledge source can be incorporated effectively into the ME learning framework and significantly improves the performance of our approach.},
keywords={},
doi={10.1093/ietisy/e90-d.7.1092},
ISSN={1745-1361},
month={July},}

Copy

TY - JOUR
TI - Zero-Anaphora Resolution in Chinese Using Maximum Entropy
T2 - IEICE TRANSACTIONS on Information
SP - 1092
EP - 1102
AU - Jing PENG
AU - Kenji ARAKI
PY - 2007
DO - 10.1093/ietisy/e90-d.7.1092
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E90-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2007
AB - In this paper, we propose a learning classifier based on maximum entropy (ME) for resolving zero-anaphora in Chinese text. Besides regular grammatical, lexical, positional and semantic features motivated by previous research on anaphora resolution, we develop two innovative Web-based features for extracting additional semantic information from the Web. The values of the two features can be obtained easily by querying the Web using some patterns. Our study shows that our machine learning approach is able to achieve an accuracy comparable to that of state-of-the-art systems. The Web as a knowledge source can be incorporated effectively into the ME learning framework and significantly improves the performance of our approach.
ER -