Few-Shot Relation Extraction on Ancient Chinese Documents
Traditional humanity scholars’ inefficient method of utilizing numerous unstructured data has hampered studies on ancient Chinese writings for several years. In this work, we aim to develop a relation extractor for ancient Chinese documents to automatically extract the relations by using unstructure...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/24/12060 |
| _version_ | 1827674272920764416 |
|---|---|
| author | Bo Li Jiyu Wei Yang Liu Yuze Chen Xi Fang Bin Jiang |
| author_facet | Bo Li Jiyu Wei Yang Liu Yuze Chen Xi Fang Bin Jiang |
| author_sort | Bo Li |
| collection | DOAJ |
| description | Traditional humanity scholars’ inefficient method of utilizing numerous unstructured data has hampered studies on ancient Chinese writings for several years. In this work, we aim to develop a relation extractor for ancient Chinese documents to automatically extract the relations by using unstructured data. To achieve this goal, we proposed a tiny ancient Chinese document relation classification (TinyACD-RC) dataset annotated by historians and contains 32 types of general relations in ShihChi (a famous Chinese history book). We also explored several methods and proposed a novel model that works well on sufficient and insufficient data scenarios, the proposed sentence encoder can simultaneously capture local and global features for a certain period. The paired attention network enhances and extracts relations between support and query instances. Experimental results show that our model achieved promising performance with scarce corpus. We also examined our model on the FewRel dataset and found that outperformed the state-of-the-art no pretraining-based models by 2.27%. |
| first_indexed | 2024-03-10T04:37:12Z |
| format | Article |
| id | doaj.art-fbfe33caad3149179c9805e4e1de784d |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T04:37:12Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-fbfe33caad3149179c9805e4e1de784d2023-11-23T03:42:37ZengMDPI AGApplied Sciences2076-34172021-12-0111241206010.3390/app112412060Few-Shot Relation Extraction on Ancient Chinese DocumentsBo Li0Jiyu Wei1Yang Liu2Yuze Chen3Xi Fang4Bin Jiang5School of Mechanical, Electrical & Information Engineering, Shandong University, Weihai 264209, ChinaSchool of Mechanical, Electrical & Information Engineering, Shandong University, Weihai 264209, ChinaSchool of Mechanical, Electrical & Information Engineering, Shandong University, Weihai 264209, ChinaSchool of Mechanical, Electrical & Information Engineering, Shandong University, Weihai 264209, ChinaSchool of Mechanical, Electrical & Information Engineering, Shandong University, Weihai 264209, ChinaSchool of Mechanical, Electrical & Information Engineering, Shandong University, Weihai 264209, ChinaTraditional humanity scholars’ inefficient method of utilizing numerous unstructured data has hampered studies on ancient Chinese writings for several years. In this work, we aim to develop a relation extractor for ancient Chinese documents to automatically extract the relations by using unstructured data. To achieve this goal, we proposed a tiny ancient Chinese document relation classification (TinyACD-RC) dataset annotated by historians and contains 32 types of general relations in ShihChi (a famous Chinese history book). We also explored several methods and proposed a novel model that works well on sufficient and insufficient data scenarios, the proposed sentence encoder can simultaneously capture local and global features for a certain period. The paired attention network enhances and extracts relations between support and query instances. Experimental results show that our model achieved promising performance with scarce corpus. We also examined our model on the FewRel dataset and found that outperformed the state-of-the-art no pretraining-based models by 2.27%.https://www.mdpi.com/2076-3417/11/24/12060ancient Chinese documentrelation extractionfew-shot learningsentence encoderdigital humanity |
| spellingShingle | Bo Li Jiyu Wei Yang Liu Yuze Chen Xi Fang Bin Jiang Few-Shot Relation Extraction on Ancient Chinese Documents Applied Sciences ancient Chinese document relation extraction few-shot learning sentence encoder digital humanity |
| title | Few-Shot Relation Extraction on Ancient Chinese Documents |
| title_full | Few-Shot Relation Extraction on Ancient Chinese Documents |
| title_fullStr | Few-Shot Relation Extraction on Ancient Chinese Documents |
| title_full_unstemmed | Few-Shot Relation Extraction on Ancient Chinese Documents |
| title_short | Few-Shot Relation Extraction on Ancient Chinese Documents |
| title_sort | few shot relation extraction on ancient chinese documents |
| topic | ancient Chinese document relation extraction few-shot learning sentence encoder digital humanity |
| url | https://www.mdpi.com/2076-3417/11/24/12060 |
| work_keys_str_mv | AT boli fewshotrelationextractiononancientchinesedocuments AT jiyuwei fewshotrelationextractiononancientchinesedocuments AT yangliu fewshotrelationextractiononancientchinesedocuments AT yuzechen fewshotrelationextractiononancientchinesedocuments AT xifang fewshotrelationextractiononancientchinesedocuments AT binjiang fewshotrelationextractiononancientchinesedocuments |