Span-based model for overlapping entity recognition and multi-relations classification in the food domain
Information extraction (IE) is an important part of the entire knowledge graph lifecycle. In the food domain, extracting information such as ingredient and cooking method from Chinese recipes is crucial to safety risk analysis and identification of ingredient. In comparison with English, due to the...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2022-03-01
|
| Series: | Mathematical Biosciences and Engineering |
| Subjects: | |
| Online Access: | https://www.aimspress.com/article/doi/10.3934/mbe.2022240?viewType=HTML |
| _version_ | 1811272558636433408 |
|---|---|
| author | Mengqi Zhang Lei Ma Yanzhao Ren Ganggang Zhang Xinliang Liu |
| author_facet | Mengqi Zhang Lei Ma Yanzhao Ren Ganggang Zhang Xinliang Liu |
| author_sort | Mengqi Zhang |
| collection | DOAJ |
| description | Information extraction (IE) is an important part of the entire knowledge graph lifecycle. In the food domain, extracting information such as ingredient and cooking method from Chinese recipes is crucial to safety risk analysis and identification of ingredient. In comparison with English, due to the complex structure, the richness of information in word combination, and lack of tense, Chinese IE is much more challenging. This dilemma is particularly prominent in the food domain with high-density knowledge, imprecise syntactic structure. However, existing IE methods focus only on the features of entities in a sentence, such as context and position, and ignore features of the entity itself and the influence of self attributes on prediction of inter entity relationship. To solve the problems of overlapping entity recognition and multi-relations classification in the food domain, we propose a span-based model known as SpIE for IE. The SpIE uses the span representation for each possible candidate entity to capture span-level features, which transforms named entity recognition (NER) into a classification mission. Besides, SpIE feeds extra information about the entity into the relation classification (RC) model by considering the effect of entity's attributes (both the entity mention and entity type) on the relationship between entity pairs. We apply SpIE on two datasets and observe that SpIE significantly outperforms the previous neural approaches due to capture the feature of overlapping entity and entity attributes, and it remains very competitive in general IE. |
| first_indexed | 2024-04-12T22:42:29Z |
| format | Article |
| id | doaj.art-460cab2f6efb47d5b18130ca2b003f76 |
| institution | Directory Open Access Journal |
| issn | 1551-0018 |
| language | English |
| last_indexed | 2024-04-12T22:42:29Z |
| publishDate | 2022-03-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | Mathematical Biosciences and Engineering |
| spelling | doaj.art-460cab2f6efb47d5b18130ca2b003f762022-12-22T03:13:40ZengAIMS PressMathematical Biosciences and Engineering1551-00182022-03-011955134515210.3934/mbe.2022240Span-based model for overlapping entity recognition and multi-relations classification in the food domainMengqi Zhang 0Lei Ma1Yanzhao Ren2Ganggang Zhang 3Xinliang Liu41. School of E-business and Logistics, Beijing Technology and Business University, Beijing 100048, China 2. National Engineering Laboratory for Agri-product Quality Traceability, Beijing Technology and Business University, Beijing 100048, China1. School of E-business and Logistics, Beijing Technology and Business University, Beijing 100048, China 2. National Engineering Laboratory for Agri-product Quality Traceability, Beijing Technology and Business University, Beijing 100048, China3. School of Computer Science and Engineering, Beijing Technology and Business University, Beijing 100048, China4. Digital Campus Construction Center, Capital Normal University, Beijing 100048, China1. School of E-business and Logistics, Beijing Technology and Business University, Beijing 100048, China 2. National Engineering Laboratory for Agri-product Quality Traceability, Beijing Technology and Business University, Beijing 100048, ChinaInformation extraction (IE) is an important part of the entire knowledge graph lifecycle. In the food domain, extracting information such as ingredient and cooking method from Chinese recipes is crucial to safety risk analysis and identification of ingredient. In comparison with English, due to the complex structure, the richness of information in word combination, and lack of tense, Chinese IE is much more challenging. This dilemma is particularly prominent in the food domain with high-density knowledge, imprecise syntactic structure. However, existing IE methods focus only on the features of entities in a sentence, such as context and position, and ignore features of the entity itself and the influence of self attributes on prediction of inter entity relationship. To solve the problems of overlapping entity recognition and multi-relations classification in the food domain, we propose a span-based model known as SpIE for IE. The SpIE uses the span representation for each possible candidate entity to capture span-level features, which transforms named entity recognition (NER) into a classification mission. Besides, SpIE feeds extra information about the entity into the relation classification (RC) model by considering the effect of entity's attributes (both the entity mention and entity type) on the relationship between entity pairs. We apply SpIE on two datasets and observe that SpIE significantly outperforms the previous neural approaches due to capture the feature of overlapping entity and entity attributes, and it remains very competitive in general IE.https://www.aimspress.com/article/doi/10.3934/mbe.2022240?viewType=HTMLinformation extractionspan-based approachoverlapping entity recognitioncategory markermulti-relations classificationentity attributes |
| spellingShingle | Mengqi Zhang Lei Ma Yanzhao Ren Ganggang Zhang Xinliang Liu Span-based model for overlapping entity recognition and multi-relations classification in the food domain Mathematical Biosciences and Engineering information extraction span-based approach overlapping entity recognition category marker multi-relations classification entity attributes |
| title | Span-based model for overlapping entity recognition and multi-relations classification in the food domain |
| title_full | Span-based model for overlapping entity recognition and multi-relations classification in the food domain |
| title_fullStr | Span-based model for overlapping entity recognition and multi-relations classification in the food domain |
| title_full_unstemmed | Span-based model for overlapping entity recognition and multi-relations classification in the food domain |
| title_short | Span-based model for overlapping entity recognition and multi-relations classification in the food domain |
| title_sort | span based model for overlapping entity recognition and multi relations classification in the food domain |
| topic | information extraction span-based approach overlapping entity recognition category marker multi-relations classification entity attributes |
| url | https://www.aimspress.com/article/doi/10.3934/mbe.2022240?viewType=HTML |
| work_keys_str_mv | AT mengqizhang spanbasedmodelforoverlappingentityrecognitionandmultirelationsclassificationinthefooddomain AT leima spanbasedmodelforoverlappingentityrecognitionandmultirelationsclassificationinthefooddomain AT yanzhaoren spanbasedmodelforoverlappingentityrecognitionandmultirelationsclassificationinthefooddomain AT ganggangzhang spanbasedmodelforoverlappingentityrecognitionandmultirelationsclassificationinthefooddomain AT xinliangliu spanbasedmodelforoverlappingentityrecognitionandmultirelationsclassificationinthefooddomain |