Dual Pointer Network for Fast Extraction of Multiple Relations in a Sentence
Relation extraction is a type of information extraction task that recognizes semantic relationships between entities in a sentence. Many previous studies have focused on extracting only one semantic relation between two entities in a single sentence. However, multiple entities in a sentence are asso...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/11/3851 |
| _version_ | 1797566435471392768 |
|---|---|
| author | Seongsik Park Harksoo Kim |
| author_facet | Seongsik Park Harksoo Kim |
| author_sort | Seongsik Park |
| collection | DOAJ |
| description | Relation extraction is a type of information extraction task that recognizes semantic relationships between entities in a sentence. Many previous studies have focused on extracting only one semantic relation between two entities in a single sentence. However, multiple entities in a sentence are associated through various relations. To address this issue, we proposed a relation extraction model based on a dual pointer network with a multi-head attention mechanism. The proposed model finds <i>n</i>-to-<i>1</i> subject–object relations using a forward object decoder. Then, it finds <i>1</i>-to-<i>n</i> subject–object relations using a backward subject decoder. Our experiments confirmed that the proposed model outperformed previous models, with an F1-score of 80.8% for the ACE (automatic content extraction) 2005 corpus and an F1-score of 78.3% for the NYT (New York Times) corpus. |
| first_indexed | 2024-03-10T19:26:46Z |
| format | Article |
| id | doaj.art-72852ac9a6224752ade1bd214ac8a86f |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T19:26:46Z |
| publishDate | 2020-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-72852ac9a6224752ade1bd214ac8a86f2023-11-20T02:27:41ZengMDPI AGApplied Sciences2076-34172020-06-011011385110.3390/app10113851Dual Pointer Network for Fast Extraction of Multiple Relations in a SentenceSeongsik Park0Harksoo Kim1Computer and Communications Engineering, Kangwon National University, Chuncheon 24341, KoreaComputer Science and Engineering, Konkuk University, Seoul 05029, KoreaRelation extraction is a type of information extraction task that recognizes semantic relationships between entities in a sentence. Many previous studies have focused on extracting only one semantic relation between two entities in a single sentence. However, multiple entities in a sentence are associated through various relations. To address this issue, we proposed a relation extraction model based on a dual pointer network with a multi-head attention mechanism. The proposed model finds <i>n</i>-to-<i>1</i> subject–object relations using a forward object decoder. Then, it finds <i>1</i>-to-<i>n</i> subject–object relations using a backward subject decoder. Our experiments confirmed that the proposed model outperformed previous models, with an F1-score of 80.8% for the ACE (automatic content extraction) 2005 corpus and an F1-score of 78.3% for the NYT (New York Times) corpus.https://www.mdpi.com/2076-3417/10/11/3851relation extractiondual pointer networkcontext-to-entity attention |
| spellingShingle | Seongsik Park Harksoo Kim Dual Pointer Network for Fast Extraction of Multiple Relations in a Sentence Applied Sciences relation extraction dual pointer network context-to-entity attention |
| title | Dual Pointer Network for Fast Extraction of Multiple Relations in a Sentence |
| title_full | Dual Pointer Network for Fast Extraction of Multiple Relations in a Sentence |
| title_fullStr | Dual Pointer Network for Fast Extraction of Multiple Relations in a Sentence |
| title_full_unstemmed | Dual Pointer Network for Fast Extraction of Multiple Relations in a Sentence |
| title_short | Dual Pointer Network for Fast Extraction of Multiple Relations in a Sentence |
| title_sort | dual pointer network for fast extraction of multiple relations in a sentence |
| topic | relation extraction dual pointer network context-to-entity attention |
| url | https://www.mdpi.com/2076-3417/10/11/3851 |
| work_keys_str_mv | AT seongsikpark dualpointernetworkforfastextractionofmultiplerelationsinasentence AT harksookim dualpointernetworkforfastextractionofmultiplerelationsinasentence |