請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/79443完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 徐宏民(Winston H. Hsu) | |
| dc.contributor.author | Jui-Heng Hsu | en |
| dc.contributor.author | 徐瑞亨 | zh_TW |
| dc.date.accessioned | 2022-11-23T09:00:38Z | - |
| dc.date.available | 2021-11-05 | |
| dc.date.available | 2022-11-23T09:00:38Z | - |
| dc.date.copyright | 2021-11-05 | |
| dc.date.issued | 2021 | |
| dc.date.submitted | 2021-10-18 | |
| dc.identifier.citation | N. Asher, J. Hunter, M. Morey, B. Farah, and S. Afantenos. Discourse structure anddialogueactsinmultipartydialogue: theSTACcorpus. InLREC,pages2721–2727.ELRA, 2016. H.Y.Chen,E.Zhou,andJ.D.Choi. Robustcoreferenceresolutionandentitylinkingon dialogues: Character identification on TV show transcripts. InCoNLL, pages216–225. ACL, 2017. Y.H. Chen and J. D. Choi. Character identification on multiparty conversation:Identifying mentions of characters in TV shows. InSIGDIAL, pages 90–100. ACL,2016. E. Choi, H. He, M. Iyyer, M. Yatskar, W.t. Yih, Y. Choi, P. Liang, and L. Zettlemoyer. QuAC:Questionansweringincontext. InEMNLP,pages2174–2184.ACL,2018. J.Devlin,M.W.Chang,K.Lee,andK.Toutanova. BERT:Pretrainingofdeepbidirectional transformers for language understanding. InNAACL:HumanLanguageTechnologies,Volume1(LongandShortPapers), pages 4171–4186. ACL, 2019. M. Henderson, B. Thomson, and J. D. Williams. The second dialog state trackingchallenge. InSIGDIAL, pages 263–272. ACL, 2014. S. Hochreiter and J. Schmidhuber. Long shortterm memory.Neuralcomputation,9:1735–80, 12 1997. S. Kim, L. F. D’Haro, R. E. Banchs, J. D. Williams, and M. Henderson.TheFourthDialogStateTrackingChallenge, pages 435–449. Springer Singapore, 2017. J. Lei, L. Yu, M. Bansal, and T. L. Berg. Tvqa: Localized, compositional videoquestion answering. InEMNLP, 2018. C. Li and J. D. Choi. Transformers to learn hierarchical contexts in multiparty dialogue for spanbased question answering. InACL, pages 5709–5714. ACL, 2020. R. Lowe, N. Pow, I. Serban, and J. Pineau. The Ubuntu dialogue corpus: A largedatasetforresearchinunstructuredmultiturndialoguesystems. InSIGDIAL,pages285–294. ACL, 2015. R. Masumura, T. Oba, H. Masataki, O. Yoshioka, and S. Takahashi. Role play dialoguetopicmodelforlanguagemodeladaptationinmultipartyconversationspeechrecognition. InICASSP, pages 4873–4877, 2014. A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin,N. Gimelshein, L. Antiga, A. Desmaison, A. Kopf, E. Yang, Z. DeVito, M. Raison,A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, and S. Chintala. Pytorch:An imperative style, highperformance deep learning library. InNIPS, pages 8024–8035. Curran Associates, Inc., 2019. PeiYun Hsueh. Audiobased unsupervised segmentation of multiparty dialogue. InICASSP, pages 5049–5052, 2008. P. Rajpurkar, J. Zhang, K. Lopyrev, and P. Liang. SQuAD: 100,000+ questions formachine comprehension of text. InEMNLP, pages 2383–2392. ACL, 2016. S.Reddy,D.Chen,andC.D.Manning. CoQA:Aconversationalquestionansweringchallenge.TransactionsoftheACL, 7:249–266, 2019. M. Richardson. Mctest: A challenge dataset for the opendomain machine comprehension of text. InEMNLP, 2013. K.Sun,D.Yu,J.Chen,D.Yu,Y.Choi,andC.Cardie. DREAM:Achallengedatasetand models for dialoguebased reading comprehension.TransactionsoftheACL,2019. T. Tsai, A. Stolcke, and M. Slaney. Multimodal addressee detection in multipartydialogue systems. InICASSP, pages 2314–2318, 2015. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser,and I. Polosukhin. Attention is all you need. InAdvancesinneuralinformationprocessingsystems, pages 5998–6008, 2017. M. Wang, N. A. Smith, and T. Mitamura. What is the Jeopardy model? a quasisynchronous grammar for QA. InEMNLPCoNLL, pages 22–32. ACL, 2007. J. Williams, A. Raux, D. Ramachandran, and A. Black. The dialog state trackingchallenge. InSIGDIAL, pages 404–413. ACL, 2013. Y. Yang, W.t. Yih, and C. Meek. WikiQA: A challenge dataset for opendomainquestion answering. InEMNLP, pages 2013–2018. ACL, 2015. Z. Yang and J. D. Choi. FriendsQA: Opendomain question answering on TV showtranscripts. InSIGDIAL, pages 188–197. ACL, 2019. E. Zhou and J. D. Choi. They exist! introducing plural mentions to coreferenceresolution and entity linking. InCOLING, pages 24–34. ACL, 2018. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/79443 | - |
| dc.description.abstract | 多人對話文本問答是話語與語言處理領域中的新興主題，其目的為根據多人對話的內容回答問題。過去的研究將對話視為一般文章並嘗試使用普通的語言模型解決問題，而忽略了對話理解當中的重要屬性，包含角色認知與情境理解。對此，我們從新的角度切入，在這篇論文中提出了兩種方法來協助這些模型。(1)得知角色資訊的多人對話模型（RAMPNet），利用了說話者與角色的資訊表現出「誰在說話」與「誰被提及」，讓我們的模型獲得角色認知的訊息。實驗顯示出此模型在多人對話文本問答中的能力與有效性，並在仰賴角色關係的問題中特別顯著。(2)影片關聯的多任務，透過利用電視劇的影片資訊來了解對話中複雜的情境。然而，實驗指出了此方式對語言模型學習角色知識的阻礙，也顯示出現行多人對話文本問答資料集的限制。 | zh_TW |
| dc.description.provenance | Made available in DSpace on 2022-11-23T09:00:38Z (GMT). No. of bitstreams: 1 U0001-1510202115515900.pdf: 713968 bytes, checksum: acb954c6b3913734213bc90b13d002f9 (MD5) Previous issue date: 2021 | en |
| dc.description.tableofcontents | Acknowledgements ii 摘要 iii Abstract iv Contents vi List of Figures viii List of Tables ix Chapter 1 Introduction 1 Chapter 2 RELATED WORK 3 2.1 Question Answering 3 2.2 MultiParty Dialogues 3 2.3 Conversational QA and MPDQA Dataset 4 Chapter 3 The Role Aware MultiParty Network 5 3.1 Motivation 5 3.2 RAMPNet Model 6 3.2.1 Role Embedding 7 3.2.2 Speaker Embedding 7 3.3 Experiments 8 3.3.1 Dataset 8 3.3.2 Implementation Details 8 3.3.3 Evaluation metrics 9 3.4 Results Analysis 9 Chapter 4 VideoRelated Multitasks on MPDQA 13 4.1 Motivation 13 4.2 Dataset 14 4.3 VideoRelated Tasks 15 4.3.1 Video Ranking 15 4.3.2 Video Reconstruction 17 4.3.3 Video Ordering 17 4.4 Experiment 18 4.5 Result Discussion 19 Chapter 5 Conclusion 22 References 23 | |
| dc.language.iso | en | |
| dc.title | 嵌入角色與影片資訊的多人對話文本問答 | zh_TW |
| dc.title | Multi-Party Dialogue Question Answering with Role and Video Information | en |
| dc.date.schoolyear | 109-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 陳文進(Hsin-Tsai Liu),余能豪(Chih-Yang Tseng),葉梅珍,陳奕廷 | |
| dc.subject.keyword | 多人對話文本問答,角色認知,指代資訊,情境理解,影片關聯多任務, | zh_TW |
| dc.subject.keyword | Multi-Party Dialogue Question Answering,Role Awareness,Coreference Information,Situation Realization,Video-related Multitask, | en |
| dc.relation.page | 26 | |
| dc.identifier.doi | 10.6342/NTU202103754 | |
| dc.rights.note | 同意授權(全球公開) | |
| dc.date.accepted | 2021-10-19 | |
| 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 |
| 顯示於系所單位： | 資訊網路與多媒體研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-1510202115515900.pdf | 697.23 kB | Adobe PDF | 檢視/開啟 |
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。