[1] Yu Jiangde, Fan Xiaozhong, Pang Wenbo, et al. Semantic role labeling based on conditional random fields [J]. Journal of Southeast University (English Edition), 2007, 23 (3): 361-364. [doi:10.3969/j.issn.1003-7985.2007.03.010]

Copy

Semantic role labeling based on conditional random fields()

Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:

23

Issue:

2007 3

Page:

361-364

Research Field:

Computer Science and Engineering

Publishing date:

2007-09-30

Info

Title:

Semantic role labeling based on conditional random fields

Author(s):

Yu Jiangde¹;  2;  Fan Xiaozhong¹;  Pang Wenbo¹;  Yu Zhengtao³

¹ School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, China
² School of Computer and Information Engineering, Anyang Normal University, Anyang 455000, China
³ School of Infor

Keywords:

semantic role labeling;  conditional random fields;  parameter estimation;  feature selection

PACS:

TP391

DOI:

10.3969/j.issn.1003-7985.2007.03.010

Abstract:

Due to the fact that semantic role labeling(SRL)is very necessary for deep natural language processing, a method based on conditional random fields(CRFs)is proposed for the SRL task.This method takes shallow syntactic parsing as the foundation, phrases or named entities as the labeled units, and the CRFs model is trained to label the predicates’ semantic roles in a sentence.The key of the method is parameter estimation and feature selection for the CRFs model. The L-BFGS algorithm was employed for parameter estimation, and three category features:features based on sentence constituents, features based on predicate, and predicate-constituent features as a set of features for the model were selected.Evaluation on the datasets of CoNLL-2005 SRL shared task shows that the method can obtain better performance than the maximum entropy model, and can achieve 80.43% precision and 63.55% recall for semantic role labeling.

References:

[1] Palmer M, Gildea D, Kingsbury P.The proposition bank:an annotated corpus of semantic roles [J].Computational Linguistics, 2005, 31(1):71-105.
[2] Baker C F, Fillmore C J, Lowe J B.The Berkeley FrameNet project [C]//Proc of ACL & COLING-1998.Montreal, Canada, 1998:86-90.
[3] Gildea D, Jurafsky D.Automatic labeling of semantic roles [J].Computational Linguistics, 2002, 28(3):245-288.
[4] Liu Huaijun, Che Wanxiang, Liu Ting.Feature engineering for Chinese semantic role labeling [J].Journal of Chinese Information Processing, 2007, 21(1):79-84.(in Chinese)
[5] Pradhan S, Hacioglu K, Krugler V, et al.Support vector learning for semantic argument classification [J].Machine Learning Journal, 2005, 60(3):11-39.
[6] Liu Ting, Che Wanxiang, Li Sheng, et al.Semantic role labeling system using maximum entropy classifier [C]//Proc of CoNLL-2005. Ann Arbor, Michigan, 2005:189-192.
[7] Che Wanxiang, Zhang Min, Liu Ting, et al.A hybrid convolution tree kernel for semantic role labeling [C]//Proc of ACL. Sydney, Australia, 2006:73-80.
[8] Lafferty J, Pereira F, McCallum A.Conditional random fields:probabilistic models for segmenting and labeling sequence data [C]//Proc of the 18th International Conference on Machine Learning.San Francisco, 2001:282-289.
[9] Sha F, Pereira F.Shallow parsing with conditional random fields [C]//Proc of Human Language Technology of NAACL.Edmonton, Canada, 2003:213-220.
[10] Byrd R H, Nocedal J, Schnabel R B.Representations of quasi-Newton matrices and their use in limited memory methods [J].Mathematical Programming, 1994, 63(2):129-156.

Memo

Memo:

Biographies: Yu Jiangde(1971—), male, graduate, lecturer, jangder@bit.edu.cn;Fan Xiaozhong(1948—), male, professor, fxz@bit.edu.cn.

Common functions