Abstract
Existing approaches to Chinese semantic role labeling (SRL) mainly adopt deep long short-term memory (LSTM) neural networks to address the long-term dependencies problem. However, deep LSTM networks cannot address the vanishing gradient problem properly. In addition, the complexity of the Chinese language, as a hieroglyphic language, decreases the performance of traditional SRL approaches to Chinese SRL. To address these problems, this paper proposes a new approach with a deep bidirectional highway LSTM network. The performance of the proposed approach is further improved by introducing the conditional random fields (CRFs) constraints and part-of-speech (POS) feature since POS tags are the classes of formal equivalents of words in linguistics. The experimental results on the commonly used Chinese Proposition Bank dataset show that the proposed approach outperforms existing approaches. With an easily acquired and reliable POS feature for practical applications, the proposed approach substantially improves Chinese SRL.
| Original language | English |
|---|---|
| Title of host publication | International Joint Conference on Neural Networks (IJCNN) 2019 |
| Editors | Plamen Angelov, Manuel Roveri |
| Place of Publication | Piscataway NJ USA |
| Publisher | IEEE, Institute of Electrical and Electronics Engineers |
| Number of pages | 6 |
| ISBN (Electronic) | 9781728119854 |
| ISBN (Print) | 9781728119861 |
| DOIs | |
| Publication status | Published - 2019 |
| Event | IEEE International Joint Conference on Neural Networks 2019 - Budapest, Hungary Duration: 14 Jul 2019 → 19 Jul 2019 https://www.ijcnn.org/ |
Conference
| Conference | IEEE International Joint Conference on Neural Networks 2019 |
|---|---|
| Abbreviated title | IJCNN 2019 |
| Country | Hungary |
| City | Budapest |
| Period | 14/07/19 → 19/07/19 |
| Internet address |
Keywords
- Chinese language
- conditional random field
- deep bidirectional highway LSTM networks
- part-of-speech
- Semantic role labeling
Cite this
}
A deep bidirectional highway long short-term memory network approach to Chinese semantic role labeling. / Xia, Qi; Yeh, Chung Hsing; Chen, Xiang Yu.
International Joint Conference on Neural Networks (IJCNN) 2019. ed. / Plamen Angelov; Manuel Roveri. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2019. 8852323.Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review
TY - GEN
T1 - A deep bidirectional highway long short-term memory network approach to Chinese semantic role labeling
AU - Xia, Qi
AU - Yeh, Chung Hsing
AU - Chen, Xiang Yu
PY - 2019
Y1 - 2019
N2 - Existing approaches to Chinese semantic role labeling (SRL) mainly adopt deep long short-term memory (LSTM) neural networks to address the long-term dependencies problem. However, deep LSTM networks cannot address the vanishing gradient problem properly. In addition, the complexity of the Chinese language, as a hieroglyphic language, decreases the performance of traditional SRL approaches to Chinese SRL. To address these problems, this paper proposes a new approach with a deep bidirectional highway LSTM network. The performance of the proposed approach is further improved by introducing the conditional random fields (CRFs) constraints and part-of-speech (POS) feature since POS tags are the classes of formal equivalents of words in linguistics. The experimental results on the commonly used Chinese Proposition Bank dataset show that the proposed approach outperforms existing approaches. With an easily acquired and reliable POS feature for practical applications, the proposed approach substantially improves Chinese SRL.
AB - Existing approaches to Chinese semantic role labeling (SRL) mainly adopt deep long short-term memory (LSTM) neural networks to address the long-term dependencies problem. However, deep LSTM networks cannot address the vanishing gradient problem properly. In addition, the complexity of the Chinese language, as a hieroglyphic language, decreases the performance of traditional SRL approaches to Chinese SRL. To address these problems, this paper proposes a new approach with a deep bidirectional highway LSTM network. The performance of the proposed approach is further improved by introducing the conditional random fields (CRFs) constraints and part-of-speech (POS) feature since POS tags are the classes of formal equivalents of words in linguistics. The experimental results on the commonly used Chinese Proposition Bank dataset show that the proposed approach outperforms existing approaches. With an easily acquired and reliable POS feature for practical applications, the proposed approach substantially improves Chinese SRL.
KW - Chinese language
KW - conditional random field
KW - deep bidirectional highway LSTM networks
KW - part-of-speech
KW - Semantic role labeling
UR - http://www.scopus.com/inward/record.url?scp=85073253859&partnerID=8YFLogxK
U2 - 10.1109/IJCNN.2019.8852323
DO - 10.1109/IJCNN.2019.8852323
M3 - Conference Paper
SN - 9781728119861
BT - International Joint Conference on Neural Networks (IJCNN) 2019
A2 - Angelov, Plamen
A2 - Roveri, Manuel
PB - IEEE, Institute of Electrical and Electronics Engineers
CY - Piscataway NJ USA
ER -