본문 바로가기
KCI 등재

한국어 문장 감성 추출 정확도 향상을 위한 BIO 태깅과 Triplet 방법론 연구

Improving the Accuracy of Extracting Sentiment in Korean Text through the BIO Tagging and Triplet Methods

외국학연구
약어 : -
2021 no.57, pp.345 - 366
DOI : 10.15755/jfs.2021..57.345
발행기관 : 중앙대학교 외국학연구소
연구분야 : 기타인문학
Copyright © 중앙대학교 외국학연구소
김원회 1 ,  이서지 2 ,  이준호 3

1주식회사 브레인벤쳐스

2주식회사 브레인벤쳐스

3주식회사 브레인벤쳐스

인용한 논문 수 :   -  
8 회 열람

Thanks to the development of artificial intelligence technology, research in the field of communication between humans and computers has been vitalized, showing tangible results. Research on the processes in which a computer understands and translates human speech and generates and responds to a sentence, based on analysis and reasoning about it is still being actively conducted. However, in this process, the representative feature that the computer has not yet completely extracted from human language is the sentiment. The sentiments, contained in human language are expressed in all areas of society and used in various ways. For example, the author of an academic thesis expresses his own theories or his claims about existing theories with positive or negative sentiment in the text. We are actively expressing our sentiments on social media that we face and participate in in our daily lives, and influence economic activity through positive or negative evaluations of purchased products. In this respect, automatic extraction of human text sentiments is a very important research field, and it is a major technology that can create economic utility as a new business model and attracts attention as a new industrial field. In general, the sentiment contained in a sentence in the speech act performed by humans can be divided into positive, negative, and neutral. In this paper, we will study the triplet extraction method, which is newly introduced in the process of developing the technology to automatically extract the above three speaker sentiments in the sentence, and BIO tagging as a basic labeling technique for this. To this end, in this paper, we will analyze the triplet-related research results announced in 2020 and 2021 in depth, track their strengths and weaknesses, and apply them to the new triplet method we are developing. Our company has researched and developed Triplet that automatically extracts the emotion of a sentence based on Korean data. As shown in <Figure 11>, the head office built and tested the Triplets for the Hangul data predicted by the GTS model trained with the Multilingual Bert model. The accuracy of Aspect and Opinion terms is 0.7 and 0.6, respectively, which is not a very high score, but it is judged that the accuracy will increase with additional data acquisition and update. The triplet accuracy is 0.3, which is still a low score. It is speculated that the reason why the triplet accuracy is low is because the training was conducted with the ‘Multilingual’ model rather than the Hangul-specific model. Therefore, we plan to train with a Korean-specific model by building a Korean training data set, and it is expected to show high accuracy soon in the future.

인공지능, 자연어처리, BIO 태깅, 감성 주체, 감성 관점, 감성
Artificial Intelligence, Natural Language Processing, BIO Tagging, Aspect, Opinion, Sentiment

  • 1. [학술대회] Bakshi, R. K. / 2016 / Opinion mining and sentiment analysis / 2016 3rd international conference on computing for sustainable global development(INDIACom) : 452 ~
  • 2. [기타] Barnes, J. / 2021 / Structured Sentiment Analysis as Dependency Graph Parsing / arXiv preprint arXiv:2105.14504
  • 3. [학술대회] Cai, H. / 2021 / Aspect-Category-Opinion-Sentiment Quadruple Extraction with Implicit Aspects and Opinions / Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processings : 340 ~
  • 4. [기타] Chen, S. / 2021 / Bidirectional Machine Reading Comprehension for Aspect Sentiment Triplet Extraction / arXiv preprint arXiv:2103.07665
  • 5. [기타] Chen, Z. / 2021 / Semantic and Syntactic Enhanced Aspect Sentiment Triplet Extraction / arXiv preprint arXiv:2106.03315
  • 6. [학술대회] Dai Hongliang / 2019 / Neutral aspect and opinion term extraction with mined rules as weak supervision / Proceedings of the 57th Confernce of the Association for Computational Linguistics, ACL 2019 / 1 : 5268 ~
  • 7. [기타] Dai, J. / 2021 / Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTa / arXiv preprint arXiv:2104.04986
  • 8. [학술대회] Dong, L. / 2014 / Adaptive recursive neural network for target-dependent twitter sentiment classification / Proceedings of the 52nd annual meeting of the association for computational linguistics / 2 : 49 ~
  • 9. [학술대회] Fan, Z. / 2019 / Target-oriented opinion words extraction with target-fused neural sequence labeling / Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies / 1 : 2509 ~
  • 10. [기타] Fang Wang / 2021 / A More Fine - Grained Aspect - Sentiment - Opinion Triplet Extraction Task / arXiv:2021.15255v4[cs.CL]
  • 11. [학술대회] Jiang, L. / 2011 / Target-dependent twitter sentiment classification / Proceedings of the 49th annual meeting of the association for computational linguistics: human language technologies : 151 ~
  • 12. [학술대회] Li Xin / 2017 / Deep multi-task learning for aspect term extraction with memory interaction / Proceedings of the 57th Confernce on Empirical Methods in Natural Language Processing : 2886 ~
  • 13. [학술지] Liu, B. / 2012 / Sentiment analysis and opinion mining / Synthesis lectures on human language technologies / 5 (1) : 1 ~ 1
  • 14. [기타] Orbach, M. / 2020 / YASO: A New Benchmark for Targeted Sentiment Analysis / arXiv preprint arXiv:2012.14541
  • 15. [학술대회] Peng, H. / 2020 / Knowing what, how and why: A near complete solution for aspect-based sentiment analysis / Proceedings of the AAAI Conference on Artificial Intelligence / 34 (05) : 8600 ~ 05
  • 16. [학술대회] Pontiki, M. / 2016 / Semeval-2016 task 5:00 Aspect based sentiment analysis / International workshop on semantic evaluation : 19 ~
  • 17. [학술대회] Sutherland, A. / 2020 / Tell Me Why You Feel That Way : Processing Compositional Dependency for Tree-LSTM Aspect Sentiment Triplet Extraction(TASTE) / International Conference on Artificial Neural Networks : 660 ~
  • 18. [기타] Tian, Y. / 2021 / Cross - Domain End - To - End Aspect-Based Sentiment Analysis with Domain-Dependent Embeddings
  • 19. [학술대회] Vo, D. T. / 2015 / Target-dependent twitter sentiment classification with rich automatic features / Twenty-fourth international joint conference on artificial intelligence : 1347 ~
  • 20. [기타] Wang, F. / 2021 / A More Fine-Grained Aspect-Sentiment-Opinion Triplet Extraction Task / arXiv preprint arXiv:2103.15255
  • 21. [기타] Wang, P. / 2021 / Explicit Interaction Network for Aspect Sentiment Triplet Extraction / arXiv preprint arXiv:2106.11148
  • 22. [기타] Wu, Z. / 2020 / Grid tagging scheme for aspect-oriented fine-grained opinion extraction / arXiv preprint arXiv:2010.04640
  • 23. [기타] Wu, Zhen / 2020 / Grid Tagging Scheme for Aspect-oriented Fine-grained Opinion Extraction / Findings of the Association for Computational Linguistics : 2576 ~
  • 24. [기타] Xu, L. / 2021 / Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction / arXiv preprint arXiv:2107.12214
  • 25. [기타] Xu, L. / 2020 / Position-aware tagging for aspect sentiment triplet extraction / arXiv preprint arXiv:2010.02609
  • 26. [기타] Xu, L. / 2020 / Aspect Sentiment Classification with Aspect-Specific Opinion Spans / EMNLP-1 : 3561 ~
  • 27. [기타] Yan, H. / 2021 / A Unified Generative Framework for Aspect-Based Sentiment Analysis / arXiv preprint arXiv:2106.04300
  • 28. [학술지] Yu Jenifei / 2019 / Global inference for aspect and opinion terms co-extraction based on multi-task neural networks / IEEE ACM Trans. Audio Speech Lang. Process / 27 (1) : 168 ~ 1
  • 29. [학술대회] Zhang, W. / 2021 / Towards Generative Aspect-Based Sentiment Analysis / Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processings : 504 ~