Semantic Relation Classification via Bidirectional LSTM Networks with Entity-Aware Attention Using Latent Entity Typing
- Title
- Semantic Relation Classification via Bidirectional LSTM Networks with Entity-Aware Attention Using Latent Entity Typing
- Author
- 최용석
- Keywords
- relation extraction; entity-aware attention; latent entity typing; end-to-end learning; visualization
- Issue Date
- 2019-06
- Publisher
- MDPI
- Citation
- SYMMETRY-BASEL, v. 11, no. 6, article no. 785
- Abstract
- Classifying semantic relations between entity pairs in sentences is an important task in natural language processing (NLP). Most previous models applied to relation classification rely on high-level lexical and syntactic features obtained by NLP tools such as WordNet, the dependency parser, part-of-speech (POS) tagger, and named entity recognizers (NER). In addition, state-of-the-art neural models based on attention mechanisms do not fully utilize information related to the entity, which may be the most crucial feature for relation classification. To address these issues, we propose a novel end-to-end recurrent neural model that incorporates an entity-aware attention mechanism with a latent entity typing (LET) method. Our model not only effectively utilizes entities and their latent types as features, but also builds word representations by applying self-attention based on symmetrical similarity of a sentence itself. Moreover, the model is interpretable by visualizing applied attention mechanisms. Experimental results obtained with the SemEval-2010 Task 8 dataset, which is one of the most popular relation classification tasks, demonstrate that our model outperforms existing state-of-the-art models without any high-level features.
- URI
- https://www.mdpi.com/2073-8994/11/6/785https://repository.hanyang.ac.kr/handle/20.500.11754/151585
- ISSN
- 2073-8994
- DOI
- 10.3390/sym11060785
- Appears in Collections:
- COLLEGE OF ENGINEERING[S](공과대학) > COMPUTER SCIENCE(컴퓨터소프트웨어학부) > Articles
- Files in This Item:
- Semantic Relation Classification via Bidirectional LSTM Networks with Entity-Aware Attention Using Latent Entity Typing.pdfDownload
- Export
- RIS (EndNote)
- XLS (Excel)
- XML