Capturing semantic features to improve Chinese event detection
Abstract Current Chinese event detection methods commonly use word embedding to capture semantic representation, but these methods find it difficult to capture the dependence relationship between the trigger words and other words in the same sentence. Based on the simple evaluation, it is known that...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-06-01
|
| Series: | CAAI Transactions on Intelligence Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/cit2.12062 |
| _version_ | 1811283132624666624 |
|---|---|
| author | Xiaobo Ma Yongbin Liu Chunping Ouyang |
| author_facet | Xiaobo Ma Yongbin Liu Chunping Ouyang |
| author_sort | Xiaobo Ma |
| collection | DOAJ |
| description | Abstract Current Chinese event detection methods commonly use word embedding to capture semantic representation, but these methods find it difficult to capture the dependence relationship between the trigger words and other words in the same sentence. Based on the simple evaluation, it is known that a dependency parser can effectively capture dependency relationships and improve the accuracy of event categorisation. This study proposes a novel architecture that models a hybrid representation to summarise semantic and structural information from both characters and words. This model can capture rich semantic features for the event detection task by incorporating the semantic representation generated from the dependency parser. The authors evaluate different models on kbp 2017 corpus. The experimental results show that the proposed method can significantly improve performance in Chinese event detection. |
| first_indexed | 2024-04-13T02:06:16Z |
| format | Article |
| id | doaj.art-9f043aaf54db4be3a28a8685740bf6f0 |
| institution | Directory Open Access Journal |
| issn | 2468-2322 |
| language | English |
| last_indexed | 2024-04-13T02:06:16Z |
| publishDate | 2022-06-01 |
| publisher | Wiley |
| record_format | Article |
| series | CAAI Transactions on Intelligence Technology |
| spelling | doaj.art-9f043aaf54db4be3a28a8685740bf6f02022-12-22T03:07:28ZengWileyCAAI Transactions on Intelligence Technology2468-23222022-06-017221922710.1049/cit2.12062Capturing semantic features to improve Chinese event detectionXiaobo Ma0Yongbin Liu1Chunping Ouyang2School of Computing University of South China Hengyang ChinaSchool of Computing University of South China Hengyang ChinaSchool of Computing University of South China Hengyang ChinaAbstract Current Chinese event detection methods commonly use word embedding to capture semantic representation, but these methods find it difficult to capture the dependence relationship between the trigger words and other words in the same sentence. Based on the simple evaluation, it is known that a dependency parser can effectively capture dependency relationships and improve the accuracy of event categorisation. This study proposes a novel architecture that models a hybrid representation to summarise semantic and structural information from both characters and words. This model can capture rich semantic features for the event detection task by incorporating the semantic representation generated from the dependency parser. The authors evaluate different models on kbp 2017 corpus. The experimental results show that the proposed method can significantly improve performance in Chinese event detection.https://doi.org/10.1049/cit2.12062grammarstext analysisnatural language processinginformation retrieval |
| spellingShingle | Xiaobo Ma Yongbin Liu Chunping Ouyang Capturing semantic features to improve Chinese event detection CAAI Transactions on Intelligence Technology grammars text analysis natural language processing information retrieval |
| title | Capturing semantic features to improve Chinese event detection |
| title_full | Capturing semantic features to improve Chinese event detection |
| title_fullStr | Capturing semantic features to improve Chinese event detection |
| title_full_unstemmed | Capturing semantic features to improve Chinese event detection |
| title_short | Capturing semantic features to improve Chinese event detection |
| title_sort | capturing semantic features to improve chinese event detection |
| topic | grammars text analysis natural language processing information retrieval |
| url | https://doi.org/10.1049/cit2.12062 |
| work_keys_str_mv | AT xiaoboma capturingsemanticfeaturestoimprovechineseeventdetection AT yongbinliu capturingsemanticfeaturestoimprovechineseeventdetection AT chunpingouyang capturingsemanticfeaturestoimprovechineseeventdetection |