상세정보
학술지
Zero-anaphora Resolution in Korean Based on Deep Language Representation Model: BERT
- 저자
- 김영태, 나동렬, 임수종
- 발행일
- 202104
- 출처
- ETRI Journal, v.43 no.2, pp.299-312
- ISSN
- 1225-6463
- 출판사
- 한국전자통신연구원 (ETRI)
- 협약과제
- 19HS3200, (엑소브레인-1세부) 휴먼 지식증강 서비스를 위한 지능진화형 WiseQA 플랫폼 기술 개발, 김현기
- 초록
- It is necessary to achieve high performance in the task of zero anaphora resolution (ZAR) for completely understanding the texts in Korean, Japanese, Chinese, and various other languages. Deep-learning-based models are being employed for building ZAR systems, owing to the success of deep learning in the recent years. However, the objective of building a high-quality ZAR system is far from being achieved even using these models. To enhance the current ZAR techniques, we fine-tuned a pre-trained bidirectional encoder representations from transformers (BERT). Notably, BERT is a general language representation model that enables systems to utilize deep bidirectional contextual information in a natural language text. It extensively exploits the attention mechanism based upon the sequence-transduction model Transformer. In our model, classification is simultaneously performed for all the words in the input word sequence to decide whether each word can be an antecedent. We seek end-to-end learning by disallowing any use of hand-crafted or dependency-parsing features. Experimental results show that compared with other models, our approach can significantly improve the performance of ZAR.
- KSP 제안 키워드
- Anaphora resolution, Attention mechanism, Contextual information, End to End(E2E), High performance, High-quality, Language representation, Learning-based, Representation model, Zero anaphora, deep learning(DL)
본 저작물은 공공누리 제4유형 : 출처표시 + 상업적 이용금지 + 변경금지 조건에 따라 이용할 수 있습니다.
