Please use this identifier to cite or link to this item:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/71351Full metadata record
| ???org.dspace.app.webui.jsptag.ItemTag.dcfield??? | Value | Language |
|---|---|---|
| dc.contributor.advisor | 許永真 | |
| dc.contributor.author | Szu-Hung Wang | en |
| dc.contributor.author | 王斯泓 | zh_TW |
| dc.date.accessioned | 2021-06-17T05:59:15Z | - |
| dc.date.available | 2019-02-15 | |
| dc.date.copyright | 2019-02-15 | |
| dc.date.issued | 2019 | |
| dc.date.submitted | 2019-02-13 | |
| dc.identifier.citation | [1] R. Agerri, M. Cuadros, S. Gaines, and G. Rigau. Opener: Open polarity enhanced named entity recognition. Procesamiento del Lenguaje Natural, 51:215–218, 2013.
[2] M. Allamanis, H. Peng, and C. A. Sutton. A convolutional attention network for extreme summarization of source code. In M. Balcan and K. Q. Weinberger, editors, Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016, volume 48 of JMLR Workshop and Conference Proceedings, pages 2091–2100. JMLR.org, 2016. [3] P. Anderson, X. He, C. Buehler, D. Teney, M. Johnson, S. Gould, and L. Zhang. Bottom-up and top-down attention for image captioning and visual question answer- ing. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pages 6077–6086. IEEE Computer Society, 2018. [4] P. Arthur, G. Neubig, and S. Nakamura. Incorporating discrete translation lexi- cons into neural machine translation. In J. Su, X. Carreras, and K. Duh, editors, Proceedings of the 2016 Conference on Empirical Methods in Natural Language Pro- cessing, EMNLP 2016, Austin, Texas, USA, November 1-4, 2016, pages 1557–1567. The Association for Computational Linguistics, 2016. [5] D. Bahdanau, K. Cho, and Y. Bengio. Neural machine translation by jointly learning to align and translate. CoRR, abs/1409.0473, 2014. [6] J. Barnes, R. Klinger, and S. Schulte im Walde. Assessing state-of-the-art sentiment models on state-of-the-art sentiment datasets. In A. Balahur, S. M. Mohammad, and E. van der Goot, editors, Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, WASSA@EMNLP 2017, Copenhagen, Denmark, September 8, 2017, pages 2–12. Association for Com- putational Linguistics, 2017. [7] X. Ding, B. Liu, and P. S. Yu. A holistic lexicon-based approach to opinion mining. In M. Najork, A. Z. Broder, and S. Chakrabarti, editors, Proceedings of the Inter- national Conference on Web Search and Web Data Mining, WSDM 2008, Palo Alto, California, USA, February 11-12, 2008, pages 231–240. ACM, 2008. [8] B. Felbo, A. Mislove, A. Søgaard, I. Rahwan, and S. Lehmann. Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm. In M. Palmer, R. Hwa, and S. Riedel, editors, Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017, Copenhagen, Denmark, September 9-11, 2017, pages 1615–1625. Association for Computational Linguistics, 2017. [9] F. A. Gers, J. Schmidhuber, and F. A. Cummins. Learning to forget: Continual prediction with LSTM. Neural Computation, 12(10):2451–2471, 2000. [10] A. Graves and J. Schmidhuber. Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Networks, 18(5-6):602–610, 2005. [11] J. Gu, Z. Lu, H. Li, and V. O. K. Li. Incorporating copying mechanism in sequence- to-sequence learning. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016, August 7-12, 2016, Berlin, Germany, Volume 1: Long Papers. The Association for Computer Linguistics, 2016. [12] K. M. Hermann, T. Kocisky ́, E. Grefenstette, L. Espeholt, W. Kay, M. Suleyman, and P. Blunsom. Teaching machines to read and comprehend. In C. Cortes, N. D. Lawrence, D. D. Lee, M. Sugiyama, and R. Garnett, editors, Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Pro- cessing Systems 2015, December 7-12, 2015, Montreal, Quebec, Canada, pages 1693– 1701, 2015. [13] M. Hu and B. Liu. Mining and summarizing customer reviews. In W. Kim, R. Ko- havi, J. Gehrke, and W. DuMouchel, editors, Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Seattle, Wash- ington, USA, August 22-25, 2004, pages 168–177. ACM, 2004. [14] M. Jabreel and A. Moreno. Eitaka at semeval-2018 task 1: An ensemble of n-channels convnet and xgboost regressors for emotion analysis of tweets. In M. Apidianaki, S. M. Mohammad, J. May, E. Shutova, S. Bethard, and M. Carpuat, editors, Proceedings of The 12th International Workshop on Semantic Evaluation, SemEval@NAACL-HLT, New Orleans, Louisiana, June 5-6, 2018, pages 193–199. Association for Computa- tional Linguistics, 2018. [15] S. Kim and E. H. Hovy. Determining the sentiment of opinions. In COLING 2004, 20th International Conference on Computational Linguistics, Proceedings of the Con- ference, 23-27 August 2004, Geneva, Switzerland, 2004. [16] Y. Kim. Convolutional neural networks for sentence classification. In A. Moschitti, B. Pang, and W. Daelemans, editors, Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, October 25-29, 2014, Doha, Qatar, A meeting of SIGDAT, a Special Interest Group of the ACL, pages 1746–1751. ACL, 2014. [17] Z. Lei, Y. Yang, and M. Yang. SAAN: A sentiment-aware attention network for sentiment analysis. In K. Collins-Thompson, Q. Mei, B. D. Davison, Y. Liu, and E. Yilmaz, editors, The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, SIGIR 2018, Ann Arbor, MI, USA, July 08- 12, 2018, pages 1197–1200. ACM, 2018. [18] B. Liu. Sentiment Analysis - Mining Opinions, Sentiments, and Emotions. Cam- bridge University Press, 2015. [19] T. Luong, H. Pham, and C. D. Manning. E ective approaches to attention-based neural machine translation. In L. M`arquez, C. Callison-Burch, J. Su, D. Pighin, and Y. Marton, editors, Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015, Lisbon, Portugal, September 17-21, 2015, pages 1412–1421. The Association for Computational Linguistics, 2015. [20] T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado, and J. Dean. Distributed rep- resentations of words and phrases and their compositionality. In C. J. C. Burges, L. Bottou, Z. Ghahramani, and K. Q. Weinberger, editors, Advances in Neural In- formation Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States., pages 3111–3119, 2013. [21] S. Mohammad, F. Bravo-Marquez, M. Salameh, and S. Kiritchenko. Semeval-2018 task 1: A ect in tweets. In M. Apidianaki, S. M. Mohammad, J. May, E. Shutova, S. Bethard, and M. Carpuat, editors, Proceedings of The 12th International Workshop on Semantic Evaluation, SemEval@NAACL-HLT, New Orleans, Louisiana, June 5-6, 2018, pages 1–17. Association for Computational Linguistics, 2018. [22] S. Mohammad, S. Kiritchenko, and X. Zhu. Nrc-canada: Building the state-of- the-art in sentiment analysis of tweets. In M. T. Diab, T. Baldwin, and M. Ba- roni, editors, Proceedings of the 7th International Workshop on Semantic Evaluation, SemEval@NAACL-HLT 2013, Atlanta, Georgia, USA, June 14-15, 2013, pages 321– 327. The Association for Computer Linguistics, 2013. [23] H. Mulki, C. B. Ali, H. Haddad, and I. Babaoglu. Tw-star at semeval-2018 task 1: Preprocessing impact on multi-label emotion classification. In M. Apidianaki, S. M. Mohammad, J. May, E. Shutova, S. Bethard, and M. Carpuat, editors, Proceedings of The 12th International Workshop on Semantic Evaluation, SemEval@NAACL-HLT, New Orleans, Louisiana, June 5-6, 2018, pages 167–171. Association for Computa- tional Linguistics, 2018. [24] T. Mullen and N. Collier. Sentiment analysis using support vector machines with diverse information sources. In Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing , EMNLP 2004, A meeting of SIGDAT, a Special Interest Group of the ACL, held in conjunction with ACL 2004, 25-26 July 2004, Barcelona, Spain, pages 412–418. ACL, 2004. [25] B. Pang and L. Lee. Seeing stars: Exploiting class relationships for sentiment catego- rization with respect to rating scales. In K. Knight, H. T. Ng, and K. Oflazer, editors, ACL 2005, 43rd Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference, 25-30 June 2005, University of Michigan, USA, pages 115–124. The Association for Computer Linguistics, 2005. [26] B. Pang and L. Lee. Opinion mining and sentiment analysis. Foundations and Trends in Information Retrieval, 2(1-2):1–135, 2007. [27] B. Pang, L. Lee, and S. Vaithyanathan. Thumbs up? sentiment classification using machine learning techniques. In Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing, EMNLP 2002, Philadelphia, PA, USA, July 6-7, 2002, 2002. [28] Q.Qian,M.Huang,J.Lei,andX.Zhu.LinguisticallyregularizedLSTMforsentiment classification. In R. Barzilay and M. Kan, editors, Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017, Vancouver, Canada, July 30 - August 4, Volume 1: Long Papers, pages 1679–1689. Association for Computational Linguistics, 2017. [29] M. J. Seo, A. Kembhavi, A. Farhadi, and H. Hajishirzi. Bidirectional attention flow for machine comprehension. CoRR, abs/1611.01603, 2016. [30] B. Shin, T. Lee, and J. D. Choi. Lexicon integrated CNN models with attention for sentiment analysis. In A. Balahur, S. M. Mohammad, and E. van der Goot, editors, Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sen- timent and Social Media Analysis, WASSA@EMNLP 2017, Copenhagen, Denmark, September 8, 2017, pages 149–158. Association for Computational Linguistics, 2017. [31] R. Socher, A. Perelygin, J. Wu, J. Chuang, C. D. Manning, A. Y. Ng, and C. Potts. Recursive deep models for semantic compositionality over a sentiment treebank. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Pro- cessing, EMNLP 2013, 18-21 October 2013, Grand Hyatt Seattle, Seattle, Wash- ington, USA, A meeting of SIGDAT, a Special Interest Group of the ACL, pages 1631–1642. ACL, 2013. [32] M. Speriosu, N. Sudan, S. Upadhyay, and J. Baldridge. Twitter polarity classification with label propagation over lexical links and the follower graph. In O. Abend, A. Ko- rhonen, A. Rappoport, and R. Reichart, editors, Proceedings of the First workshop on Unsupervised Learning in NLP@EMNLP 2011, Edinburgh, Scotland, July 30, 2011, pages 53–63. Association for Computational Linguistics, 2011. [33] M. Taboada, J. Brooke, M. Tofiloski, K. D. Voll, and M. Stede. Lexicon-based methods for sentiment analysis. Computational Linguistics, 37(2):267–307, 2011. [34] K. S. Tai, R. Socher, and C. D. Manning. Improved semantic representations from tree-structured long short-term memory networks. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL 2015, July 26-31, 2015, Beijing, China, Volume 1: Long Papers, pages 1556–1566. The Association for Computer Linguistics, 2015. [35] O. Uryupina, B. Plank, A. Severyn, A. Rotondi, and A. Moschitti. Sentube: A corpus for sentiment analysis on youtube social media. In N. Calzolari, K. Choukri, T. De- clerck, H. Loftsson, B. Maegaard, J. Mariani, A. Moreno, J. Odijk, and S. Piperidis, editors, Proceedings of the Ninth International Conference on Language Resources and Evaluation, LREC 2014, Reykjavik, Iceland, May 26-31, 2014., pages 4244–4249. European Language Resources Association (ELRA), 2014. [36] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin. Attention is all you need. In I. Guyon, U. von Luxburg, S. Bengio, H. M. Wallach, R. Fergus, S. V. N. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Processing Systems 30: Annual Conference on Neural Infor- mation Processing Systems 2017, 4-9 December 2017, Long Beach, CA, USA, pages 6000–6010, 2017. [37] T. Wilson, J. Wiebe, and P. Ho mann. Recognizing contextual polarity in phrase- level sentiment analysis. In HLT/EMNLP 2005, Human Language Technology Con- ference and Conference on Empirical Methods in Natural Language Processing, Pro- ceedings of the Conference, 6-8 October 2005, Vancouver, British Columbia, Canada, pages 347–354. The Association for Computational Linguistics, 2005. [38] K. Xu, J. Ba, R. Kiros, K. Cho, A. C. Courville, R. Salakhutdinov, R. S. Zemel, and Y. Bengio. Show, attend and tell: Neural image caption generation with vi- sual attention. In F. R. Bach and D. M. Blei, editors, Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6-11 July 2015, volume 37 of JMLR Workshop and Conference Proceedings, pages 2048–2057. JMLR.org, 2015. [39] T. Yanase, K. Yanai, M. Sato, T. Miyoshi, and Y. Niwa. bunji at semeval-2016 task 5: Neural and syntactic models of entity-attribute relationship for aspect-based sentiment analysis. In S. Bethard, D. M. Cer, M. Carpuat, D. Jurgens, P. Nakov, and T. Zesch, editors, Proceedings of the 10th International Workshop on Semantic Evaluation, SemEval@NAACL-HLT 2016, San Diego, CA, USA, June 16-17, 2016, pages 289–295. The Association for Computer Linguistics, 2016. [40] Z. Yang, X. He, J. Gao, L. Deng, and A. J. Smola. Stacked attention networks for image question answering. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, June 27-30, 2016, pages 21–29. IEEE Computer Society, 2016. [41] W. Yin and H. Schu ̈tze. An exploration of embeddings for generalized phrases. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014, June 22-27, 2014, Baltimore, MD, USA, Student Research Workshop, pages 41–47. The Association for Computer Linguistics, 2014. [42] J. Yoon and H. Kim. Multi-channel lexicon integrated cnn-bilstm models for senti- ment analysis. In L. Ku and Y. Tsao, editors, Proceedings of the 29th Conference on Computational Linguistics and Speech Processing, ROCLING 2017, Taipei, Taiwan, November 27-28, 2017, pages 244–253. The Association for Computational Linguis- tics and Chinese Language Processing (ACLCLP), 2017. [43] L. Zhang, S. Wang, and B. Liu. Deep learning for sentiment analysis: A survey. Wiley Interdiscip. Rev. Data Min. Knowl. Discov., 8(4), 2018. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/71351 | - |
| dc.description.abstract | 情緒分析 (sentiment analysis) 是一個找出文字中的情緒與情感的重要任務，常用於分析句子中的情緒與感情。此問題常被視為一種分類的問題，利用深度神經網路模型可以達到很好的成果，注意力機制也被證實有很好的效果。再者，先前研究也指出情緒辭典對情緒分析問題上有很好的成效。然而，情緒辭典並沒有適當地被應用在先前的研究中。
本篇論文探索了情緒引導之注意力機制，以完整利用情緒辭典並將情緒辭典結合在注意力機制中，藉此幫助分類。我們提出兩種結合方法，第一，為了有效利用情緒辭典，我們轉換情緒詞典中的情緒值，使其成為一組增強注意力權重係數，以最小化原本模型內的注意力權重係數之錯誤。第二，我們提出了情緒多頭注意力機制，我們使用從情緒值轉換而來的注意力權重係數，做為第二組注意力頭，以協助模型關注更多資訊。我們實驗在六組情緒分析資料集上，結果顯示此方法準確度皆超越先前最佳的模型，相較於先前的分數提升0.12%到8.12%。 | zh_TW |
| dc.description.abstract | Sentiment analysis is an important task, which extracts sentiment, emotion or affect in text. The problem is often treated as a classification problem for which deep neural methods have been well explored and attention mechanisms have generated promising performance. Studies have shown that lexicon is highly effective for sentiment analysis. However, lexicon has not been fully utilized by the previous methods. No existing method integrates lexicon into the attention mechanism effectively to solve the problem.
This thesis explores the sentiment-guided attention mechanism, which integrates lexicon into attention mechanism and proposes two approaches. First, to utilize sentiment lexicons, we transform lexicon values into guiding weights to minimize the error of attention weights. Second, we propose sentiment multi-head attention to help the model jointly attend to sentiment information provided by the transformed lexicon values. Experiments show that our models outperform state-of-the-art models on six sentiment analysis benchmarks with improved accuracy of 0.12% to 8.12%. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-17T05:59:15Z (GMT). No. of bitstreams: 1 ntu-108-R05944025-1.pdf: 2459603 bytes, checksum: 33c534ff8408c961359fb7046ab9fc6a (MD5) Previous issue date: 2019 | en |
| dc.description.tableofcontents | Acknowledgments ................................ i
Abstract ................................ iii List of Figures ................................ viii List of Tables ................................ x Chapter 1 Introduction ................................ 1 1.1 Background ................................ 1 1.2 Motivation................................. 3 1.3 Objective ................................. 4 1.4 Outline of the Thesis........................... 4 Chapter 2 Related Work ................................ 5 2.1 Sentiment Analysis ............................ 5 2.2 Attention Mechanism ........................... 6 2.3 Neural Model with Sentiment Lexicon .................. 7 Chapter 3 Sentiment Analysis with Lexicon ................................ 9 3.1 Problem Statement ............................ 9 3.2 Proposed Solution ............................. 11 Chapter 4 Sentiment-Guided Attention Mechanism ................................ 14 4.1 System Architecture ........................... 14 4.2 The Baseline Attention-Based Model .................. 15 4.3 Sentiment-Guided Weights Generation Model ................................ 17 4.4 Sentiment Boosted Attention Approach ................................ 19 4.4.1 Hard Boost Method ....................... 19 4.4.2 Soft Boost Method ........................ 21 4.4.3 Merge Boost Method ................................ 23 4.5 Sentiment Multi-Head Attention Approach ................................ 24 Chapter 5 Experiments ................................ 27 5.1 Lexicons and Datasets .......................... 27 5.1.1 Lexicons ................................ 27 5.1.2 Stanford Sentiment Treebank ................................ 29 5.1.3 OpenNER ................................ 29 5.1.4 Sentube Datasets ................................ 29 5.1.5 SemEval-2018 Task1: Affect in Tweets ................................ 30 5.2 Experimental Setup ................................ 30 5.3 Experimental Results ................................ 31 5.4 Model Analysis ................................ 33 5.4.1 Effect of Sentiment Boosted Attention ................................ 33 5.4.2 Effect of Sentiment Multi-Head Attention ................................ 36 5.4.3 Randomness in Deep Learning ................................ 38 5.4.4 Robustness of the Model ................................ 40 Chapter 6 Conclusion ................................ 42 6.1 Summary of Contributions ................................ 42 6.2 Future Work ................................ 43 Bibliography ................................ 44 | |
| dc.language.iso | en | |
| dc.subject | 情感分析 | zh_TW |
| dc.subject | 情緒分類 | zh_TW |
| dc.subject | 情緒辭典 | zh_TW |
| dc.subject | 注意力機制 | zh_TW |
| dc.subject | 類神經網路 | zh_TW |
| dc.subject | Lexicon | en |
| dc.subject | Attention Mechanism | en |
| dc.subject | Sentiment Analysis | en |
| dc.subject | Emotion Classification | en |
| dc.subject | Neural Networks | en |
| dc.title | 以情緒導引強化注意力機制於情緒分析之研究 | zh_TW |
| dc.title | Sentiment-Guided Attention Mechanism for Sentiment Analysis | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 107-1 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 劉昭麟,李宏毅,古倫維,陳維超 | |
| dc.subject.keyword | 情感分析,情緒分類,情緒辭典,注意力機制,類神經網路, | zh_TW |
| dc.subject.keyword | Sentiment Analysis,Emotion Classification,Lexicon,Attention Mechanism,Neural Networks, | en |
| dc.relation.page | 52 | |
| dc.identifier.doi | 10.6342/NTU201900557 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2019-02-14 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊網路與多媒體研究所 | zh_TW |
| Appears in Collections: | 資訊網路與多媒體研究所 | |
Files in This Item:
| File | Size | Format | |
|---|---|---|---|
| ntu-108-1.pdf Restricted Access | 2.4 MB | Adobe PDF |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.