請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/88534完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 陳縕儂 | zh_TW |
| dc.contributor.advisor | Yun-Nung Chen | en |
| dc.contributor.author | 林栢衛 | zh_TW |
| dc.contributor.author | Po-Wei Lin | en |
| dc.date.accessioned | 2023-08-15T16:43:43Z | - |
| dc.date.available | 2023-11-09 | - |
| dc.date.copyright | 2023-08-15 | - |
| dc.date.issued | 2023 | - |
| dc.date.submitted | 2023-08-02 | - |
| dc.identifier.citation | [1] A. Albalak, V. Embar, Y.-L. Tuan, L. Getoor, and W. Y. Wang. D-REX: Dialogue relation extraction with explanations. In Proceedings of the 4th Workshop on NLP for Conversational AI, pages 34–46, 2022.
[2] V. Ashish, S. Noam, P. Niki, U. Jakob, J. Llion, N. G. Aidan, K. Lukasz, and P. Illia. Attention is all you need. arXiv:1706.03762, 2017. [3] S. Bengio, O. Vinyals, N. Jaitly, and N. Shazeer. Scheduled sampling for sequence prediction with recurrent neural networks. In Advances in Neural Information Processing Systems, pages 1171–1179, 2015. [4] H. Chen, P. Hong, W. Han, N. Majumder, and S. Poria. Dialogue relation extraction with document-level heterogeneous graph attention networks. arXiv preprint arXiv:2009.05092, 2020. [5] A. D. Cohen, S. Rosenman, and Y. Goldberg. Relation classification as two-way span prediction. arXiv preprint arXiv:2010.04829, 2020. [6] Q. Jia, H. Huang, and K. Q. Zhu. Ddrel: A new dataset for interpersonal relation classification in dyadic dialogues. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 13125–13133, 2021. [7] J. D. M.-W. C. Kenton and L. K. Toutanova. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT, pages 4171–4186, 2019. [8] P.-N. Kung, T.-H. Yang, Y.-C. Chen, S.-S. Yin, and Y.-N. Chen. Zero-shot rationalization by multi-task transfer learning from question answering. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2187–2197, 2020. [9] B. Lee and Y. S. Choi. Graph based network with contextualized representations of turns in dialogue. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 443–455, 2021. [10] K. Lee, S. Salant, T. Kwiatkowski, A. Parikh, D. Das, and J. Berant. Learning recurrent span representations for extractive question answering. arXiv preprint arXiv:1611.01436, 2016. [11] G. Nan, Z. Guo, I. Sekulić, and W. Lu. Reasoning with latent structure refinement for document-level relation extraction. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1546–1557, 2020. [12] B. Peng, X. Li, J. Gao, J. Liu, K.-F. Wong, and S.-Y. Su. Deep dyna-q: Integrating planning for task-completion dialogue policy learning. arXiv preprint arXiv:1801.06176, 2018. [13] P. Rajpurkar, J. Zhang, K. Lopyrev, and P. Liang. Squad: 100,000+ questions for machine comprehension of text. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, 2016. [14] S.-Y. Su, X. Li, J. Gao, J. Liu, and Y.-N. Chen. Discriminative deep dyna-q: Robust planning for dialogue policy learning. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3813–3823, 2018. [15] S.-Y. Su, K.-L. Lo, Y.-T. Yeh, and Y.-N. Chen. Natural language generation by hierarchical decoding with linguistic patterns. In Proceedings of The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2018. [16] F. Xue, A. Sun, H. Zhang, and E. S. Chng. GDPNet: Refining latent multi-view graph for relation extraction. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 14194–14202, 2021. [17] F. Xue, A. Sun, H. Zhang, J. Ni, and E.-S. Chng. An embarrassingly simple model for dialogue relation extraction. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 6707–6711. IEEE, 2022. [18] D. Yu, K. Sun, C. Cardie, and D. Yu. Dialogue-based relation extraction. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4927 4940, 2020. [19] Y.-N. C. Ze-Song Xu. Zero-shot dialogue relation extraction by relating explainable triggers and relation names. In The 5th Workshop on Natural Language Processing for Conversational AI (NLP4ConvAI 2023), 2023. [20] Y. Zhang, V. Zhong, D. Chen, G. Angeli, and C. D. Manning. Position-aware attention and supervised data improve slot filling. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 35–45, 2017. [21] W. Zhou and M. Chen. An improved baseline for sentence-level relation extraction. arXiv preprint arXiv:2102.01373, 2021. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/88534 | - |
| dc.description.abstract | 對話系統關係抽取的旨在識別任意兩個實體在給定的對話中的關係。在對話的過程中，語者可能會透過明示或暗示的線索表達出彼此之間的關係，這種線索可以被稱作觸發詞。然而，並不是所有的目標資料都有觸發詞的標記，所以想要利用這種資訊來增進表現是具有挑戰性的。
因此，本篇論文提出了使用有標記觸發詞的資料學習識別觸發詞，再將已習得的尋找觸發詞的能力遷移到其他的資料上已得到更好的表現。實驗顯示本論文所提出的方法可以有效在訓練時未看過的關係上提升關係抽取的表現，也展示了所提出的尋找觸發詞的模型在不同領域和資料上的遷移能力。 | zh_TW |
| dc.description.abstract | The goal of dialogue relation extraction (DRE) is to identify the relation between two entities in a given dialogue. During conversations, speakers may expose their relations to certain entities by explicit or implicit clues, such pieces of evidence called “triggers." However, trigger annotations may not be always available for the target data, so it is challenging to leverage such information for enhancing performance.
Therefore, this paper proposes to learn how to identify triggers from the data with trigger annotations and then transfer the trigger-finding capability to other datasets for better performance. The experiments show that the proposed approach is capable of improving relation extraction performance of unseen relations and also demonstrate the transferability of our proposed trigger-finding model across different domains and datasets. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2023-08-15T16:43:43Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2023-08-15T16:43:43Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 致謝 . . . . . . . . . . . . . . . . . . . . . . . . . . . . i
摘要 . . . . . . . . . . . . . . . . . . . . . . . . . . . . iii Abstract . . . . . . . . . . . . . . . . . . . . . . . . . . . . v Contents . . . . . . . . . . . . . . . . . . . . . . . . . . . . vii List of Figures . . . . . . . . . . . . . . . . . . . . . . . . . . . . xi List of Tables . . . . . . . . . . . . . . . . . . . . . . . . . . . . xiii Chapter 1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 Thesis Structure . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 Chapter 2 Background . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 2.1 Transformer . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 2.1.1 Self-Attention Mechanism. . . . . . . . . . . . . . . . . . . . . . . 6 2.1.2 Multi-Head Attention . . . . . . . . . . . . . . . . . . . . . . . . . 6 2.2 BERT . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 2.2.1 Masked Language Modeling . . . . . . . . . . . . . . . . . . . . . 7 2.2.2 Next Sentence Prediction . . . . . . . . . . . . . . . . . . . . . . . 7 Chapter 3 Related Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 3.1 Relation Extraction . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 3.2 Relation Extraction Methods . . . . . . . . . . . . . . . . . . . . . . 10 3.3 Graph-based Methods . . . . . . . . . . . . . . . . . . . . . . . . . 10 3.4 BERT-based methods . . . . . . . . . . . . . . . . . . . . . . . . . . 10 Chapter 4 Proposed Method . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 4.1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 4.2 Problem Formulation . . . . . . . . . . . . . . . . . . . . . . . . . . 13 4.3 TREND . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 4.3.1 Explicit Trigger Gate . . . . . . . . . . . . . . . . . . . . . . . . . 14 4.3.2 Trigger Prediction . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 4.3.3 Relation Prediction . . . . . . . . . . . . . . . . . . . . . . . . . . 15 4.4 Training Objective . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 4.4.1 Cross Entropy Loss . . . . . . . . . . . . . . . . . . . . . . . . . . 15 4.4.2 Supervised Joint Learning . . . . . . . . . . . . . . . . . . . . . . . 16 4.4.3 Transfer Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 Chapter 5 Experiments . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 5.1 Datasets . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 5.1.1 DialogRE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 5.1.2 DDRel . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 5.2 Training Details . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 5.2.1 Hyperparameters . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 5.2.2 Cost of Time . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 5.3 Setting . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 5.3.1 Compared Models . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 5.4 Result Analysis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 5.4.1 Results of Supervised Joint Learning . . . . . . . . . . . . . . . . . 22 5.4.2 Results of Transfer Learning . . . . . . . . . . . . . . . . . . . . . 23 5.4.3 Ablation Study . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24 Chapter 6 Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25 6.1 Generalization of Unseen Relations . . . . . . . . . . . . . . . . . . 25 6.1.1 Assessment of Transfer Learning on Unseen Relations . . . . . . . 25 6.1.2 Exploring the Predicted Triggers for Unseen Relations . . . . . . . 26 6.1.3 Qualitative Study . . . . . . . . . . . . . . . . . . . . . . . . . . . 27 Chapter 7 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29 References . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31 | - |
| dc.language.iso | en | - |
| dc.subject | 對話系統 | zh_TW |
| dc.subject | 自然語言理解 | zh_TW |
| dc.subject | 關係抽取 | zh_TW |
| dc.subject | 遷移式學習 | zh_TW |
| dc.subject | Dialogue System | en |
| dc.subject | Natural Language Understanding | en |
| dc.subject | Transfer Learning | en |
| dc.subject | Relation Extraction | en |
| dc.title | 基於對話中的觸發詞增強對話系統關係抽取網路 | zh_TW |
| dc.title | Trigger-Enhanced Relation Extraction Network for Dialogues | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 111-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 李宏毅;陳尚澤;馬偉雲 | zh_TW |
| dc.contributor.oralexamcommittee | Hung-Yi Lee;Shang-Tse Chen;Wei-Yun Ma | en |
| dc.subject.keyword | 自然語言理解,關係抽取,對話系統,遷移式學習, | zh_TW |
| dc.subject.keyword | Natural Language Understanding,Relation Extraction,Dialogue System,Transfer Learning, | en |
| dc.relation.page | 34 | - |
| dc.identifier.doi | 10.6342/NTU202302575 | - |
| dc.rights.note | 同意授權(限校園內公開) | - |
| dc.date.accepted | 2023-08-04 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 資訊工程學系 | - |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-111-2.pdf 授權僅限NTU校內IP使用（校園外請利用VPN校外連線服務） | 516.88 kB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。