Extraction of Joint Entity and Relationships with Soft Pruning and GlobalPointer
In recent years, scholars have paid increasing attention to the joint entity and relation extraction. However, the most difficult aspect of joint extraction is extracting overlapping triples. To address this problem, we propose a joint extraction model based on Soft Pruning and GlobalPointer, short...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/13/6361 |
| _version_ | 1797481121061011456 |
|---|---|
| author | Jianming Liang Qing He Damin Zhang Shuangshuang Fan |
| author_facet | Jianming Liang Qing He Damin Zhang Shuangshuang Fan |
| author_sort | Jianming Liang |
| collection | DOAJ |
| description | In recent years, scholars have paid increasing attention to the joint entity and relation extraction. However, the most difficult aspect of joint extraction is extracting overlapping triples. To address this problem, we propose a joint extraction model based on Soft Pruning and GlobalPointer, short for SGNet. In the first place, the BERT pretraining model is used to obtain the text word vector representation with contextual information, and then the local and non-local information of the word vector is obtained through graph operations. Specifically, to address the lack of information caused by the rule-based pruning strategies, we utilize the Gaussian Graph Generator and the attention-guiding layer to construct a fully connected graph. This process is called soft pruning for short. Then, to achieve node message passing and information integration, we employ GCNs and a thick connection layer. Next, we use the GlobalPointer decoder to convert triple extraction into quintuple extraction to tackle the problem of problematic overlapping triples extraction. The GlobalPointer decoder, unlike the typical feedforward neural network (FNN), can perform joint decoding. In the end, to evaluate the model performance, the experiment was carried out on two public datasets: the NYT and WebNLG. The experiments show that SGNet performs substantially better on overlapping extraction and achieves good results on two publicly available datasets. |
| first_indexed | 2024-03-09T22:09:57Z |
| format | Article |
| id | doaj.art-f8232fe0995d41538930b32c8f4c1cf9 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T22:09:57Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-f8232fe0995d41538930b32c8f4c1cf92023-11-23T19:35:26ZengMDPI AGApplied Sciences2076-34172022-06-011213636110.3390/app12136361Extraction of Joint Entity and Relationships with Soft Pruning and GlobalPointerJianming Liang0Qing He1Damin Zhang2Shuangshuang Fan3College of Big Data & Information Engineering, Guizhou University, Guiyang 550025, ChinaCollege of Big Data & Information Engineering, Guizhou University, Guiyang 550025, ChinaCollege of Big Data & Information Engineering, Guizhou University, Guiyang 550025, ChinaDepartment of Information and Electronics, Science and Technology College of NCHU, Nanchang 332020, ChinaIn recent years, scholars have paid increasing attention to the joint entity and relation extraction. However, the most difficult aspect of joint extraction is extracting overlapping triples. To address this problem, we propose a joint extraction model based on Soft Pruning and GlobalPointer, short for SGNet. In the first place, the BERT pretraining model is used to obtain the text word vector representation with contextual information, and then the local and non-local information of the word vector is obtained through graph operations. Specifically, to address the lack of information caused by the rule-based pruning strategies, we utilize the Gaussian Graph Generator and the attention-guiding layer to construct a fully connected graph. This process is called soft pruning for short. Then, to achieve node message passing and information integration, we employ GCNs and a thick connection layer. Next, we use the GlobalPointer decoder to convert triple extraction into quintuple extraction to tackle the problem of problematic overlapping triples extraction. The GlobalPointer decoder, unlike the typical feedforward neural network (FNN), can perform joint decoding. In the end, to evaluate the model performance, the experiment was carried out on two public datasets: the NYT and WebNLG. The experiments show that SGNet performs substantially better on overlapping extraction and achieves good results on two publicly available datasets.https://www.mdpi.com/2076-3417/12/13/6361joint extractionoverlapping entityoverlapping relation extractionsoft pruningGlobalPointer |
| spellingShingle | Jianming Liang Qing He Damin Zhang Shuangshuang Fan Extraction of Joint Entity and Relationships with Soft Pruning and GlobalPointer Applied Sciences joint extraction overlapping entity overlapping relation extraction soft pruning GlobalPointer |
| title | Extraction of Joint Entity and Relationships with Soft Pruning and GlobalPointer |
| title_full | Extraction of Joint Entity and Relationships with Soft Pruning and GlobalPointer |
| title_fullStr | Extraction of Joint Entity and Relationships with Soft Pruning and GlobalPointer |
| title_full_unstemmed | Extraction of Joint Entity and Relationships with Soft Pruning and GlobalPointer |
| title_short | Extraction of Joint Entity and Relationships with Soft Pruning and GlobalPointer |
| title_sort | extraction of joint entity and relationships with soft pruning and globalpointer |
| topic | joint extraction overlapping entity overlapping relation extraction soft pruning GlobalPointer |
| url | https://www.mdpi.com/2076-3417/12/13/6361 |
| work_keys_str_mv | AT jianmingliang extractionofjointentityandrelationshipswithsoftpruningandglobalpointer AT qinghe extractionofjointentityandrelationshipswithsoftpruningandglobalpointer AT daminzhang extractionofjointentityandrelationshipswithsoftpruningandglobalpointer AT shuangshuangfan extractionofjointentityandrelationshipswithsoftpruningandglobalpointer |