A Global Deep Reranking Model for Semantic Role Classification
Summary :
The current approaches to semantic role classification usually first define a representation vector for a candidate role and feed the vector into a deep neural network to perform classification. The representation vector contains some lexicalization features like word embeddings, lemmar embeddings. From linguistics, the semantic role frame of a sentence is a joint structure with strong dependencies between arguments which is not considered in current deep SRL systems. Therefore, this paper proposes a global deep reranking model to exploit these strong dependencies. The evaluation experiments on the CoNLL 2009 shared tasks show that our system can outperforms a strong local system significantly that does not consider role dependency relations.
- Publication
- IEICE TRANSACTIONS on Information Vol.E104-D No.7 pp.1063-1066
- Publication Date
- 2021/07/01
- Publicized
- 2021/04/15
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2020EDL8164
- Type of Manuscript
- LETTER
- Category
- Natural Language Processing
Authors
Haitong YANG
Central China Normal University
Guangyou ZHOU
Central China Normal University
Tingting HE
Central China Normal University
Maoxi LI
Jiangxi Normal University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Haitong YANG, Guangyou ZHOU, Tingting HE, Maoxi LI, "A Global Deep Reranking Model for Semantic Role Classification" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 7, pp. 1063-1066, July 2021, doi: 10.1587/transinf.2020EDL8164.
Abstract: The current approaches to semantic role classification usually first define a representation vector for a candidate role and feed the vector into a deep neural network to perform classification. The representation vector contains some lexicalization features like word embeddings, lemmar embeddings. From linguistics, the semantic role frame of a sentence is a joint structure with strong dependencies between arguments which is not considered in current deep SRL systems. Therefore, this paper proposes a global deep reranking model to exploit these strong dependencies. The evaluation experiments on the CoNLL 2009 shared tasks show that our system can outperforms a strong local system significantly that does not consider role dependency relations.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020EDL8164/_p
Copy
@ARTICLE{e104-d_7_1063,
author={Haitong YANG, Guangyou ZHOU, Tingting HE, Maoxi LI, },
journal={IEICE TRANSACTIONS on Information},
title={A Global Deep Reranking Model for Semantic Role Classification},
year={2021},
volume={E104-D},
number={7},
pages={1063-1066},
abstract={The current approaches to semantic role classification usually first define a representation vector for a candidate role and feed the vector into a deep neural network to perform classification. The representation vector contains some lexicalization features like word embeddings, lemmar embeddings. From linguistics, the semantic role frame of a sentence is a joint structure with strong dependencies between arguments which is not considered in current deep SRL systems. Therefore, this paper proposes a global deep reranking model to exploit these strong dependencies. The evaluation experiments on the CoNLL 2009 shared tasks show that our system can outperforms a strong local system significantly that does not consider role dependency relations.},
keywords={},
doi={10.1587/transinf.2020EDL8164},
ISSN={1745-1361},
month={July},}
Copy
TY - JOUR
TI - A Global Deep Reranking Model for Semantic Role Classification
T2 - IEICE TRANSACTIONS on Information
SP - 1063
EP - 1066
AU - Haitong YANG
AU - Guangyou ZHOU
AU - Tingting HE
AU - Maoxi LI
PY - 2021
DO - 10.1587/transinf.2020EDL8164
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2021
AB - The current approaches to semantic role classification usually first define a representation vector for a candidate role and feed the vector into a deep neural network to perform classification. The representation vector contains some lexicalization features like word embeddings, lemmar embeddings. From linguistics, the semantic role frame of a sentence is a joint structure with strong dependencies between arguments which is not considered in current deep SRL systems. Therefore, this paper proposes a global deep reranking model to exploit these strong dependencies. The evaluation experiments on the CoNLL 2009 shared tasks show that our system can outperforms a strong local system significantly that does not consider role dependency relations.
ER -
English
