심층학습을 이용한 문서요약의 연구방법 분석
A Study on the Text Summarization based on Deep Neural Network
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
In this study, we discuss the basic technology of Text Summarization based on the deep neural network for natural language processing(NLP). The text summarization task is divided into an extractive summary and an abstractive summary. The extractive summary is a method of extracting a summary of the words used in the input document in the output text, and the abstractive summary is a problem of understanding the input statement and generating a sentence of the same content. The abstractive sentence generation system is based on the encoder-decoder model with attention mechanism, and a selector that can select input sentence is added. The Copy network and Pointer network are the special mechanisms for selector. Such selector systems can make text summarization to be the hybrid form of abstractive and extractive summary. In the future, we expect that accuracy of text summarization will be improved by adding reinforcement learning method.
Abstract
In this study, we discuss the basic technology of Text Summarization based on the deep neural network for natural language processing(NLP). The text summarization task is divided into an extractive summary and an abstractive summary. The extractive summary is a method of extracting a summary of the words used in the input document in the output text, and the abstractive summary is a problem of understanding the input statement and generating a sentence of the same content. The abstractive sentence generation system is based on the encoder-decoder model with attention mechanism, and a selector that can select input sentence is added. The Copy network and Pointer network are the special mechanisms for selector. Such selector systems can make text summarization to be the hybrid form of abstractive and extractive summary. In the future, we expect that accuracy of text summarization will be improved by adding reinforcement learning method.
참고문헌 (14)
- 권영대, "문장 수반 관계를 고려한 문서 요약", 정보과학회논문지, 44(2), pp.179~185 (2017), 한국정보과학회
- 백수진, "VAE를 이용한 의미적 연결 관계 기반 다중 문서 요약 기법", 디지털융복합연구, 15(12), pp.341~347 (2017), 한국디지털정책학회[DOI]
- 지인영, "인공지능과 인문학(언어학)", 국제언어인문학회 학술대회논문집 (2017), 국제언어인문학회
- 지인영, "심층학습을 이용한 기계번역 기술과 정확도 연구", 인문언어, 19(2), pp.24~46 (2017), 국제언어인문학회
- 최경호, "복사 방법론과 입력 추가 구조를 이용한 End-to-End 한국어 문서요약", 정보과학회논문지, 44(5), pp.503~509 (2017), 한국정보과학회
- Abigail See, "Get To The Point: Summarization with Pointer-Generator Networks", ACL, pp.1073~1083 (2017)
- Alexander M. Rush, "A Neural Attention Model for Abstractive Sentence Summarization", EMNLP, pp.379~389 (2015)
- Jiatao Gu, "Incorporating copying mechanism in sequence-to-sequence learning", ACL, pp.1631~1640 (2016)
- Okazaki Naoaki, "自然言語処理におけるDeep Learning", 일본 전기전자정보통신학회 종합학술대회 논문집 (2017)
- Oriol Vinyals, "Pointer Networks", arXiv:1506.03134v1 Jun 2015, arXiv:1506.03134v2, ~ (2017)
- Qingyu Zhou, "Selective Encoding for Abstractive Sentence Summarization", ACL, pp.1095~1104 (2017)
- Ramesh Nallapati, "Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond", SIGNLL, pp.280~290 (2016)
- Y.J. Kumar, "A revieew on Automatic text summarization Approaches", Journal of computer science (2016), Science Publications
- 坪井 祐太, "深層学習による自然言語処理" (2017), 講談社