Research on Chinese predicate head recognition based on Highway-BiLSTM network
Aiming at the problem of difficult recognition and uniqueness of Chinese predicate head, a Highway-BiLSTM model was proposed.Firstly, multi-layer BiLSTM networks were used to capture multi-granular semantic dependence in a sentence.Then, a Highway network was adopted to alleviate the problem of grad...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2021-01-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2021027/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841539291476393984 |
|---|---|
| author | Ruizhang HUANG Wenfan JIN Yanping CHEN Yongbin QIN Qinghua ZHENG |
| author_facet | Ruizhang HUANG Wenfan JIN Yanping CHEN Yongbin QIN Qinghua ZHENG |
| author_sort | Ruizhang HUANG |
| collection | DOAJ |
| description | Aiming at the problem of difficult recognition and uniqueness of Chinese predicate head, a Highway-BiLSTM model was proposed.Firstly, multi-layer BiLSTM networks were used to capture multi-granular semantic dependence in a sentence.Then, a Highway network was adopted to alleviate the problem of gradient disappearance.Finally, the output path was optimized by a constraint layer which was designed to guarantee the uniqueness of predicate head.The experimental results show that the proposed method effectively improves the performance of predicate head recognition. |
| format | Article |
| id | doaj-art-906e3df9ec1949409987738e1cb96373 |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2021-01-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-906e3df9ec1949409987738e1cb963732025-01-14T07:21:30ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2021-01-014210010759739748Research on Chinese predicate head recognition based on Highway-BiLSTM networkRuizhang HUANGWenfan JINYanping CHENYongbin QINQinghua ZHENGAiming at the problem of difficult recognition and uniqueness of Chinese predicate head, a Highway-BiLSTM model was proposed.Firstly, multi-layer BiLSTM networks were used to capture multi-granular semantic dependence in a sentence.Then, a Highway network was adopted to alleviate the problem of gradient disappearance.Finally, the output path was optimized by a constraint layer which was designed to guarantee the uniqueness of predicate head.The experimental results show that the proposed method effectively improves the performance of predicate head recognition.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2021027/predicate headhighway connectionBiLSTMuniqueness |
| spellingShingle | Ruizhang HUANG Wenfan JIN Yanping CHEN Yongbin QIN Qinghua ZHENG Research on Chinese predicate head recognition based on Highway-BiLSTM network Tongxin xuebao predicate head highway connection BiLSTM uniqueness |
| title | Research on Chinese predicate head recognition based on Highway-BiLSTM network |
| title_full | Research on Chinese predicate head recognition based on Highway-BiLSTM network |
| title_fullStr | Research on Chinese predicate head recognition based on Highway-BiLSTM network |
| title_full_unstemmed | Research on Chinese predicate head recognition based on Highway-BiLSTM network |
| title_short | Research on Chinese predicate head recognition based on Highway-BiLSTM network |
| title_sort | research on chinese predicate head recognition based on highway bilstm network |
| topic | predicate head highway connection BiLSTM uniqueness |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2021027/ |
| work_keys_str_mv | AT ruizhanghuang researchonchinesepredicateheadrecognitionbasedonhighwaybilstmnetwork AT wenfanjin researchonchinesepredicateheadrecognitionbasedonhighwaybilstmnetwork AT yanpingchen researchonchinesepredicateheadrecognitionbasedonhighwaybilstmnetwork AT yongbinqin researchonchinesepredicateheadrecognitionbasedonhighwaybilstmnetwork AT qinghuazheng researchonchinesepredicateheadrecognitionbasedonhighwaybilstmnetwork |