簡易檢索 / 詳目顯示

回結果列表
研究生： 劉秝瑋
Liu, Li-Wei
論文名稱： 以句子雙重情境表示法建模改進情緒原因句配對擷取之研究
Clause Dual-Context Representation Learning for Improving End-to-End Emotion-Cause Pair Extraction
指導教授： 柯佳伶
Koh, Jia-Ling
口試委員： 陳良弼 吳宜鴻 范耀中 柯佳伶
口試日期： 2021/08/17
學位類別： 碩士
Master
系所名稱： 資訊工程學系
Department of Computer Science and Information Engineering
論文出版年： 2021
畢業學年度： 109
語文別： 中文
論文頁數： 55
中文關鍵詞： 情緒原因句配對擷取 、深度學習 、自然語言理解 、多任務學習
研究方法: 實驗設計法
DOI URL： http://doi.org/10.6345/NTNU202101310
論文種類： 學術論文
相關次數： 點閱：134  下載：13 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 針對情緒原因句配對擷取任務，本論文提出一個基於句子雙重情境表示法建模的模型。本研究提出的模型中對文本中同一個句子分別學習情緒句及原因句情境表示法，並採用多任務學習的訓練方式，使模型在訓練時除了考慮情緒原因句配對預測任務，同時考慮情緒句及原 因句預測子任務，以學習語意更完整的情緒原因句配對表示法進行配對預測。此外，本研究考慮情緒句及原因句在文本中正負樣本數不平衡的問題，因此採用損失函數權重調整策略，使模型在訓練後能提高情緒句及原因句預測子任務的回復率，連帶提升情緒原因句配對擷取任務的預測效果。實驗結果顯示，本論文方法以兩個圖神經網路學習句子雙重情境表示法，並配合損失函數權重調整策略，較相關研究以單個圖神經網路學習情境表示法的模型，在情緒原因句配對擷取任務達到更佳的效果。

    附表目錄 ........................................................................................................................................ iv 附圖目錄 .......................................................................................................................................... v 第一章 緒論................................................................................................................................. 1 1.1 研究動機與目的 .......................................................................................................... 1 1.2 研究方法 ........................................................................................................................ 4 1.3 論文架構 ........................................................................................................................ 7 第二章 文獻探討 ....................................................................................................................... 8 2.1 情緒原因句擷取(Emotion cause extraction ,ECE) .................................... 8 2.1.1 基於規則式(Rule-Based)的情緒原因句擷取 .................................................................. 8 2.1.2 機器學習(Machine Learning)方法的情緒原因句擷取 ................................................. 9 2.1.3 深度學習(Deep Learning)方法的情緒原因句擷取 ..................................................... 10 2.2 情緒原因句配對擷取（Emotion-cause pair extraction ,ECPE）.............................. 12 2.2.1 兩步驟 two step 處理的情緒原因句配對擷取 .............................................................. 12 2.2.2 端對端(End to end)的情緒原因句配對擷取 ................................................................. 14 第三章 句子雙重情境表示法學習模型....................................................................................... 18 3.1 問題定義 .................................................................................................................................... 18 3. 2 模型架構 ................................................................................................................................... 19 3.2.1 句子的雙重情境表示法建模 .............................................................................................. 20 (1) 卷積神經網路 Convolutional Neural Network CNN) ................................................. 20 (2) 圖神經網路 Graph Neural Network GNN) ..................................................................... 21 (3) 預測情緒句及原因句的子任務 .............................................................................................. 22 3.2.2 句子配對表示法的學習與配對排序 ................................................................................. 23 3.2.3 損失函數 ................................................................................................................................. 24 第四章 實驗結果與探討 ................................................................................................................ 26 4.1 資料集來源與參數設定 .......................................................................................................... 26 4.2 評估指標及評估標準 .............................................................................................................. 28 4.2.1 評估指標的計算公式說明 .................................................. 28 4.2.2 評估的預測任務 ................................................................................................................... 29 4.3 實驗結果與討論..........................................................................................30 4.3.1 採用句子雙重情境表示法模型架構的效果評估 ............................... 30 4.3.2 在損失函數採用權重調整策略的效果評估 ........................................ ..........34 4.3.3 2-gnn模型對不同特性資料的預測效果評估.................................................. 36 4.3.4 個案實驗討論 ............................................................................................. 47 第五章 結論與未來研究方向 ...................................................................................................... 49 參考文獻 .......................................................................................................................................... 50

    [1] Alm, C. O., D. Roth and R. Sproat. 2005. Emotions from Text: Machine Learning for Text-based Emotion Prediction. In Proceedings of the Human Language Technology Conference and the 2005 Conference on Empirical Methods in Natural Language Processing, Vancouver, Canada, 6-8 October,pp. 579-586.
    [2] Mihalcea, R. and H. Liu. 2006. A Corpus-based Approach to Finding Happiness. In Proceedings of the AAAI Spring Symposium on Computational Approaches to Weblogs.
    [3] Tokuhisa, R., K. Inui, and Y. Matsumoto. 2008. Emotion Classification Using Massive Examples Extracted from the Web. In Proceedings of COLING.
    [4] Alm, C. O. 2009. Affect in Text and Speech. VDM Verlag: Saarbrücken.
    [5] Sophia Yat Mei Lee, Ying Chen, and Chu-Ren Huang. 2010. A Text-driven Rule-based System for Emotion Cause Detection. In Proceedings of the NAACL HLT 2010 Workshop on Computational Approaches to Analysis and Generation of Emotion in Text, pages 45-53.
    [6] Irene Russo, Tommaso Caselli, Francesco Rubino, Ester Boldrini, and Patricio Martinez-Barco. 2011. EMOCause: An Easy-agaptable Approach to Emotion Cause Contexts. In Proceedings of the 2nd Workshop on Computational Approaches to Subjectivity and Sentiment Analysis, ACL-HLT 2011, pages 153–160.
    [7] Alena Neviarouskaya and Masaki Aono. 2013. Extracting causes of emotions from text. In Proceedings of IJCNLP.
    [8] Diman Ghazi, Diana Inkpen, and Stan Szpakowicz. 2015. Detecting emotion stimuli in emotion-bearing sentences. In Proceedings of CICLing.
    [9] Lin Gui, Dongyin Wu, Ruifeng Xu, Qin Lu, and Yu Zhou. 2016a. Event-driven emotion cause extraction with corpus construction. In Proceedings of Empirical Methods in Natural Language Processing(EMNLP), pages 1639–1649.
    [10] Lin Gui, Ruifeng Xu, Qin Lu, Dongyin Wu, and Yu Zhou. 2016b. Emotion cause extraction, a challenging task with corpus construction. In Proceedings of Chinese National Conference on Social Media Processing,pages 98–109.
    [11] Ruifeng Xu, Jiannan Hu, Qin Lu, Dongyin Wu, and Lin Gui. 2017. An ensemble approach for emotion cause detection with event extraction and multikernel svms. Tsinghua Science and Technology, 22(6):646–659.
    [12] Rui Xia and Zixiang Ding. 2019. Emotion-Cause Pair Extraction: A New Task to Emotion Analysis in Texts. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1003-1012.
    [13] Penghui Wei, Jiahao Zhao, and Wenji Mao.Effective Inter-Clause Modeling for End-to-End Emotion-Cause Pair Extraction. In Proceedings of ACL 2020: The 58th Annual Meeting of the Association for Computational Linguistics, pages 3171--3181.
    [14] Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL-HLT 2019, pages 4171–4186.
    [15] Yang Liu and Mirella Lapata. 2019. Text summarization with pretrained encoders. In Proceedings of EMNLP-IJCNLP.
    [16] Peter Turney. Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews. In Proceedings of the Association for Computational Linguistics: 417–424. 2002.
    [17] Bo Pang, Lillian Lee, and Shivakumar Vaithyanathan. Thumbs up? Sentiment Classification using Machine Learning Techniques. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) 2002.
    [18] Weiyuan Li and Hua Xu. 2014. Text-based Emotion Classification Using Emotion Cause Extraction. Expert Systems with Applications, 41(4): 1742-1749.
    [19] Lin Gui, Jianna Hu, Yulan He, Ruifeng Xu, Qin Lu, and Jiachen. Du. 2017. A Question Answering Approach to Emotion Cause Extraction. In Proceedings of Empirical Methods in Natural Language Processing, pages 1639-1649.
    [20] Lin Gui, Li Yuan, Ruifeng Xu, Bin Liu, Qin Lu, and Yu Zhou. 2014. Emotion Cause Detection with Linguistic Construction in Chinese Weibo Text. In Proceedings of Natural Language Processing and Chinese Computing, pages 457-464.
    [21] Shuangyong Song and Yao Meng. 2015. Detecting Concept-level Emotion Cause in Microblogging. In Proceedings of the 24th International Conference on World Wide Web, pages 119-120.
    [22] Shuntaro Yada, Kazushi Ikeda, Keiichiro Hoashi, and Kyo Kageura. 2017. A Bootstrap Method for Automatic Rule Acquisition on Emotion Cause Extraction. In Proceedings of IEEE International Conference on Data Mining Workshops, pages 414-421.
    [23] Ying Chen, Wenjun Hou, Xiyao Cheng, and Shoushan Li. 2018b. Joint Learning for Emotion Classification and Emotion Cause Detection. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 646-651.
    [24] Xiangju Li, Kaisong Song, Shi Feng, Daling Wang, and Yifei Zhang, 2018. A Co-attention Neural Network Model for Emotion Cause Analysis with Emotional Context Awareness. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4752-4757.
    [25] Xinyi Yu,Wenge Rong, Zhuo Zhang, Yuanxin Ouyang, and Zhang Xiong. 2019. Multiple level hierarchical network-based clause selection for emotion cause extraction. In Proceedings of IEEE Access, 7(1):9071–9079.
    [26] Zixiang Ding, Rui Xia, and Jianfei Yu. 2020. ECPE2D: Emotion-cause pair extraction based on joint two-dimensional representation, interaction and prediction. In Proceedings of Association for Computational Linguistics (ACL), pages 3161–3170
    [27] Z. Ding, R. Xia, and J. Yu, "End-to-end emotion-cause pair extraction based on sliding window multi-label learning". In Proceedings of Empirical Methods Natural Lang. Process. (EMNLP), pp. 3574-3583, Nov. 2020.
    [28] Bo Xu, Hongfei Lin, Yuan Lin, Yufeng Diao, Liang Yang, and Kan Xu. 2019. Extracting emotion causes using learning to rank methods from an information retrieval perspective. In Proceedings of IEEE Access.
    [29] Rui Xia, Mengran Zhang, and Zixiang Ding, 2019. RTHN: A RNN-Transformer Hierarchical Network for Emotion Cause Extraction. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, pages 5285-5291.
    [30] Ashish Vanwani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Lilon Jones, Aidan N.Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. In Proceedings of the 31st International Conference on Neural Information Processing Systems, pages 6000-6010.
    [31] Chuang Fan, Hongyu Yan, Jiachen Du, Lin Gui, Lidong Bing, Min Yang, Ruifeng Xu, and Ruibin Mao. 2019. A Knowledge Regularized Hierarchical Approach for Emotion Cause Analysis. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pages 5618–5628.
    [32] Xiangju Li, Shi Feng, Daling Wang, and Yifei Zhang. 2019. Context-aware emotion cause analysis with multi-attention-based neural network. In Proceedings of Knowledge-Based Systems, pages 205-218.
    [33] Jiaxing Hu, Shumin Shi, and Heyan Huang. 2019. Combining External Sentiment Knowledge for Emotion Cause Detection. In Proceedings of Natural Language Processing and Chinese Computing, pages 711-722.
    [34] Chaofa Yuan, Chuang Fan, Jianzhu Bao, and Ruifeng Xu. 2020. Emotion-Cause Pair Extraction as Sequence Labeling Based on A Novel Tagging Scheme. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), page 3568-3573
    [35] Haolin Song, Chen Zhang, Qiuchi Li, and Dawei Song. 2020. An End-to-End Multi-Task Learning to Link Framework for Emotion-Cause Pair Extraction. In Proceedings of Computation and Language (cs.CL).
    [36] Hao Tang, Donghong Ji, and Qiji Zhou. 2020. Joint multi-level attentional model for emotion detection and emotion-cause pair extraction. Neurocomputing, page 329-340.

    下載圖示
    QR CODE