Combining the Attention Network and Semantic Representation for Chinese Verb Metaphor Identification
Metaphor is the central issue of language and thinking. Metaphor identification plays a significant preliminary role in the field of machine translation, reading comprehension, and automatic summarization, making it a focus of natural language processing. Recently, research into Chinese verb metapho...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8782559/ |
| _version_ | 1818924005812338688 |
|---|---|
| author | Dongyu Zhang Hongfei Lin Xikai Liu Heting Zhang Shaowu Zhang |
| author_facet | Dongyu Zhang Hongfei Lin Xikai Liu Heting Zhang Shaowu Zhang |
| author_sort | Dongyu Zhang |
| collection | DOAJ |
| description | Metaphor is the central issue of language and thinking. Metaphor identification plays a significant preliminary role in the field of machine translation, reading comprehension, and automatic summarization, making it a focus of natural language processing. Recently, research into Chinese verb metaphor identification has become a widespread concern. The main problem is that the usage of semantic resources is relatively simple, and there is a lack of deep semantic support. Therefore, this paper proposes a word representation method suitable for metaphor classification tasks, which combines the traditional word vector with structural information from the Synonym Thesaurus, so that the word vector can contain the abstraction degree of the word in the metaphor. On this basis, we propose a verb metaphor attention network based on subject-predicate and verb-object relationships, which gives full consideration to the global syntactic information when we perform LSTM encoding and calculate the weight of each word. At the same time, it can facilitate the understanding of literalness and non-literalness. The experimental results show that the identification effect improves on the existing results, indicating that word representation combining semantic resources and attention network can improve the verb metaphor identification performance. |
| first_indexed | 2024-12-20T02:18:27Z |
| format | Article |
| id | doaj.art-2abb881a5af04d10a567f5e0680f263f |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T02:18:27Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-2abb881a5af04d10a567f5e0680f263f2022-12-21T19:56:52ZengIEEEIEEE Access2169-35362019-01-01713710313711010.1109/ACCESS.2019.29321368782559Combining the Attention Network and Semantic Representation for Chinese Verb Metaphor IdentificationDongyu Zhang0https://orcid.org/0000-0002-7683-5560Hongfei Lin1Xikai Liu2Heting Zhang3Shaowu Zhang4School of Software, Dalian University of Technology, Dalian, ChinaSchool of Computer Science and Technology, Dalian University of Technology, Dalian, ChinaSchool of Computer Science and Technology, Dalian University of Technology, Dalian, ChinaSchool of Software, Dalian University of Technology, Dalian, ChinaSchool of Computer Science and Technology, Dalian University of Technology, Dalian, ChinaMetaphor is the central issue of language and thinking. Metaphor identification plays a significant preliminary role in the field of machine translation, reading comprehension, and automatic summarization, making it a focus of natural language processing. Recently, research into Chinese verb metaphor identification has become a widespread concern. The main problem is that the usage of semantic resources is relatively simple, and there is a lack of deep semantic support. Therefore, this paper proposes a word representation method suitable for metaphor classification tasks, which combines the traditional word vector with structural information from the Synonym Thesaurus, so that the word vector can contain the abstraction degree of the word in the metaphor. On this basis, we propose a verb metaphor attention network based on subject-predicate and verb-object relationships, which gives full consideration to the global syntactic information when we perform LSTM encoding and calculate the weight of each word. At the same time, it can facilitate the understanding of literalness and non-literalness. The experimental results show that the identification effect improves on the existing results, indicating that word representation combining semantic resources and attention network can improve the verb metaphor identification performance.https://ieeexplore.ieee.org/document/8782559/Attention networkmetaphor identificationmetaphor datasetsemantic representation |
| spellingShingle | Dongyu Zhang Hongfei Lin Xikai Liu Heting Zhang Shaowu Zhang Combining the Attention Network and Semantic Representation for Chinese Verb Metaphor Identification IEEE Access Attention network metaphor identification metaphor dataset semantic representation |
| title | Combining the Attention Network and Semantic Representation for Chinese Verb Metaphor Identification |
| title_full | Combining the Attention Network and Semantic Representation for Chinese Verb Metaphor Identification |
| title_fullStr | Combining the Attention Network and Semantic Representation for Chinese Verb Metaphor Identification |
| title_full_unstemmed | Combining the Attention Network and Semantic Representation for Chinese Verb Metaphor Identification |
| title_short | Combining the Attention Network and Semantic Representation for Chinese Verb Metaphor Identification |
| title_sort | combining the attention network and semantic representation for chinese verb metaphor identification |
| topic | Attention network metaphor identification metaphor dataset semantic representation |
| url | https://ieeexplore.ieee.org/document/8782559/ |
| work_keys_str_mv | AT dongyuzhang combiningtheattentionnetworkandsemanticrepresentationforchineseverbmetaphoridentification AT hongfeilin combiningtheattentionnetworkandsemanticrepresentationforchineseverbmetaphoridentification AT xikailiu combiningtheattentionnetworkandsemanticrepresentationforchineseverbmetaphoridentification AT hetingzhang combiningtheattentionnetworkandsemanticrepresentationforchineseverbmetaphoridentification AT shaowuzhang combiningtheattentionnetworkandsemanticrepresentationforchineseverbmetaphoridentification |