Semantic role Lableing system using maximum entropy Classifier

Ting Liu; Wanxiang Che; Sheng Li; Yuxuan Hu; Huaijun Liu

doi:10.3115/1706543.1706578

Semantic role Lableing system using maximum entropy Classifier

Ting Liu^*
, Wanxiang Che
, Sheng Li
, Yuxuan Hu
, Huaijun Liu

^*Corresponding author for this work

School of Computer Science and Technology, Harbin Institute of Technology

Research output: Contribution to conference › Paper › peer-review

29 Scopus citations

Abstract

A maximum entropy classifier is used in our semantic role labeling system, which takes syntactic constituents as the labeling units. The maximum entropy classifier is trained to identify and classify the predicates' semantic arguments together. Only the constituents with the largest probability among embedding ones are kept. After predicting all arguments which have matching constituents in full parsing trees, a simple rule-based post-processing is applied to correct the arguments which have no matching constituents in these trees. Some useful features and their combinations are evaluated.

Original language	English
Pages	189-192
Number of pages	4
DOIs	https://doi.org/10.3115/1706543.1706578
State	Published - 2005
Externally published	Yes
Event	9th Conference on Computational Natural Language Learning, CoNLL 2005 - Ann Arbor, MI, United States Duration: 29 Jun 2005 → 30 Jun 2005

Conference

Conference	9th Conference on Computational Natural Language Learning, CoNLL 2005
Country/Territory	United States
City	Ann Arbor, MI
Period	29/06/05 → 30/06/05

Access to Document

10.3115/1706543.1706578

Cite this

@conference{f5d5177dbd3a4704b7866d1c32727e3d,

title = "Semantic role Lableing system using maximum entropy Classifier",

abstract = "A maximum entropy classifier is used in our semantic role labeling system, which takes syntactic constituents as the labeling units. The maximum entropy classifier is trained to identify and classify the predicates' semantic arguments together. Only the constituents with the largest probability among embedding ones are kept. After predicting all arguments which have matching constituents in full parsing trees, a simple rule-based post-processing is applied to correct the arguments which have no matching constituents in these trees. Some useful features and their combinations are evaluated.",

author = "Ting Liu and Wanxiang Che and Sheng Li and Yuxuan Hu and Huaijun Liu",

year = "2005",

doi = "10.3115/1706543.1706578",

language = "英语",

pages = "189--192",

note = "9th Conference on Computational Natural Language Learning, CoNLL 2005 ; Conference date: 29-06-2005 Through 30-06-2005",

}

TY - CONF

T1 - Semantic role Lableing system using maximum entropy Classifier

AU - Liu, Ting

AU - Che, Wanxiang

AU - Li, Sheng

AU - Hu, Yuxuan

AU - Liu, Huaijun

PY - 2005

Y1 - 2005

N2 - A maximum entropy classifier is used in our semantic role labeling system, which takes syntactic constituents as the labeling units. The maximum entropy classifier is trained to identify and classify the predicates' semantic arguments together. Only the constituents with the largest probability among embedding ones are kept. After predicting all arguments which have matching constituents in full parsing trees, a simple rule-based post-processing is applied to correct the arguments which have no matching constituents in these trees. Some useful features and their combinations are evaluated.

AB - A maximum entropy classifier is used in our semantic role labeling system, which takes syntactic constituents as the labeling units. The maximum entropy classifier is trained to identify and classify the predicates' semantic arguments together. Only the constituents with the largest probability among embedding ones are kept. After predicting all arguments which have matching constituents in full parsing trees, a simple rule-based post-processing is applied to correct the arguments which have no matching constituents in these trees. Some useful features and their combinations are evaluated.

UR - https://www.scopus.com/pages/publications/35348978627

U2 - 10.3115/1706543.1706578

DO - 10.3115/1706543.1706578

M3 - 论文

AN - SCOPUS:35348978627

SP - 189

EP - 192

T2 - 9th Conference on Computational Natural Language Learning, CoNLL 2005

Y2 - 29 June 2005 through 30 June 2005

ER -

Semantic role Lableing system using maximum entropy Classifier

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this