請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/72872完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 林守德(Shou-De Lin) | |
| dc.contributor.author | Wei Chen | en |
| dc.contributor.author | 陳偉 | zh_TW |
| dc.date.accessioned | 2021-06-17T07:08:47Z | - |
| dc.date.available | 2019-07-24 | |
| dc.date.copyright | 2019-07-24 | |
| dc.date.issued | 2019 | |
| dc.date.submitted | 2019-07-23 | |
| dc.identifier.citation | [1] P. Anand, M. Walker, R. Abbott, J. E. F. Tree, R. Bowmani, and M. Minor. Cats rule and dogs drool!: Classifying stance in online debate. In Proceedings of the 2nd workshop on computational approaches to subjectivity and sentiment analysis, pages 1–9. Association for Computational Linguistics, 2011.
[2] I. Augenstein, T. Rockta ̈schel, A. Vlachos, and K. Bontcheva. Stance detection with bidirectional conditional encoding. arXiv preprint arXiv:1606.05464, 2016. [3] R. Baeza-Yates, B. Ribeiro-Neto, et al. Modern information retrieval, volume 463. ACM press New York, 1999. [4] C. J. Burges. From rank net to lambda rank to lambda mart: An overview. Learning, 11(23-581):81, 2010. [5] R. Caruana. Multitask learning. Machine learning, 28(1):41–75, 1997. [6] D. Chen and C. Manning. A fast and accurate dependency parser using neural networks. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pages 740–750, 2014. [7] O. Chum, J. Philbin, J. Sivic, M. Isard, and A. Zisserman. Total recall: Automatic query expansion with a generative feature model for object retrieval. In 2007 IEEE 11th International Conference on Computer Vision, pages 1–8. IEEE, 2007. [8] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova. Bert: Pre-training of deep bidi- rectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018. [9] M. Dias and K. Becker. An heuristics-based, weakly-supervised approach for classi- fication of stance in tweets. In 2016 IEEE/WIC/ACM International Conference on Web Intelligence (WI), pages 73–80. IEEE, 2016. [10] J. Du, R. Xu, Y. He, and L. Gui. Stance classification with target-specific neural attention networks. International Joint Conferences on Artificial Intelligence, 2017. [11] D. Erhan, Y. Bengio, A. Courville, P.-A. Manzagol, P. Vincent, and S. Bengio. Why does unsupervised pre-training help deep learning? Journal of Machine Learning Research, 11(Feb):625–660, 2010. [12] G. W. Furnas, T. K. Landauer, L. M. Gomez, and S. T. Dumais. The vocabulary problem in human-system communication. Communications of the ACM, 30(11):964– 971, 1987. [13] J. Howard and S. Ruder. Universal language model fine-tuning for text classification. arXiv preprint arXiv:1801.06146, 2018. [14] S. Ioffe. Improved consistent sampling, weighted minhash and l1 sketching. In 2010 IEEE International Conference on Data Mining, pages 246–255. IEEE, 2010. [15] K. Johnson and D. Goldwasser. “all i know about politics is what i read in twit- ter”: Weakly supervised models for extracting politicians’ stances from twitter. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 2966–2977, 2016. [16] Y. Kim. Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882, 2014. [17] P. Krejzl and J. Steinberger. Uwb at semeval-2016 task 6: stance detection. In Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), pages 408–412, 2016. [18] X. Liu, P. He, W. Chen, and J. Gao. Multi-task deep neural networks for natural language understanding. arXiv preprint arXiv:1901.11504, 2019. [19] T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado, and J. Dean. Distributed repre- sentations of words and phrases and their compositionality. In Advances in neural information processing systems, pages 3111–3119, 2013. [20] A. Misra, B. Ecker, T. Handleman, N. Hahn, and M. Walker. Nlds-ucsc at semeval-2016 task 6: A semi-supervised approach to detecting stance in tweets. In Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), pages 420–427, 2016. [21] J. Pennington, R. Socher, and C. Manning. Glove: Global vectors for word rep- resentation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pages 1532–1543, 2014. [22] M. E. Peters, M. Neumann, M. Iyyer, M. Gardner, C. Clark, K. Lee, and L. Zettle- moyer. Deep contextualized word representations. arXiv preprint arXiv:1802.05365, 2018. [23] M. Pontiki, D. Galanis, H. Papageorgiou, I. Androutsopoulos, S. Manandhar, A.-S. Mohammad, M. Al-Ayyoub, Y. Zhao, B. Qin, O. De Clercq, et al. Semeval-2016 task 5: Aspect based sentiment analysis. In Proceedings of the 10th international workshop on semantic evaluation (SemEval-2016), pages 19–30, 2016. [24] Y. Qi, D. S. Sachan, M. Felix, S. J. Padmanabhan, and G. Neubig. When and why are pre-trained word embeddings useful for neural machine translation? arXiv preprint arXiv:1804.06323, 2018. [25] D. Qin, S. Gammeter, L. Bossard, T. Quack, and L. Van Gool. Hello neighbor: Accurate object retrieval with k-reciprocal nearest neighbors. In CVPR 2011, pages 777–784. IEEE, 2011. [26] A. Radford, K. Narasimhan, T. Salimans, and I. Sutskever. Improving language understanding by generative pre-training. URL https://s3-us-west-2. amazon- aws. com/openai-assets/research-covers/languageunsupervised/language understand- ing paper. pdf, 2018. [27] S. Robertson, H. Zaragoza, et al. The probabilistic relevance framework: Bm25 and beyond. Foundations and Trends⃝R in Information Retrieval, 3(4):333–389, 2009. [28] G. Salton. The smart system. Retrieval Results and Future Plans, 1971. [29] S. Somasundaran and J. Wiebe. Recognizing stances in ideological on-line debates. In Proceedings of the NAACL HLT 2010 Workshop on Computational Approaches to Analysis and Generation of Emotion in Text, pages 116–124. Association for Computational Linguistics, 2010. [30] F. Song and W. B. Croft. A general language model for information retrieval. In Proceedings of the eighth international conference on Information and knowledge management, pages 316–321. ACM, 1999. [31] D. Sridhar, J. Foulds, B. Huang, L. Getoor, and M. Walker. Joint models of disagreement and stance in online debate. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Con- ference on Natural Language Processing (Volume 1: Long Papers), volume 1, pages 116–125, 2015. [32]A.Vaswani, N.Shazeer, N.Parmar, J.Uszkoreit, L.Jones, A.N.Gomez, L [33] M. A. Walker, P. Anand, R. Abbott, and R. Grant. Stance classification using dialogic properties of persuasion. In Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 592–596. Association for Computational Linguistics, 2012. [34] D. Yin, Y. Hu, J. Tang, T. Daly, M. Zhou, H. Ouyang, J. Chen, C. Kang, H. Deng, C. Nobata, et al. Ranking relevance in yahoo search. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 323–332. ACM, 2016. [35] Z. Zheng, K. Chen, G. Sun, and H. Zha. A regression framework for learning ranking functions using relative relevance judgments. In Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval, pages 287–294. ACM, 2007. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/72872 | - |
| dc.description.abstract | 新聞立場檢索是從搜索中的到和搜索輸入具有相同立場的新聞，若能快速得到各種特定立場的新聞，有助於人們快速理解不同立場新聞下的價值觀，也有助於對社會輿論的長期趨勢進行分析，有相當的價值，而現有大多數搜索引擎的返回內容需要人工去分析判斷新聞的立場。對這類問題，本文提出了半監督多任務學習方法和重排序方法。半監督多任務學習方法在不引入標記資料的情況下，利用新聞結構信息與多任務學習提升了模型的性能。重排序挖掘排序對象之間的關係，不需要新的標記資料，不需對特定的任務的專家理解，得到更精準的排序結果，並可普適于其它排序任務。 | zh_TW |
| dc.description.abstract | Stance news retrieval aims to obtain news, which is related and having the same stance with query, from huge amounts of news. Retrieving news with specific stance can be beneficial, which helps to understand values from different stance, and also helps to analyze the long-term trend of public opinions. We introduce Semi-supervised multi-task learning for stance classification and an re-ranking method for news ranking. The semi-supervised multi-task Learning, a transfer learning method which leverages the structure information in news, significantly outperform the base model without new labeled data. The re-ranking method leverages the relationship between the ranking items, it does not require any human knowledge or any labeled data, improves the ranking performance and is applicable in other ranking task. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-17T07:08:47Z (GMT). No. of bitstreams: 1 ntu-108-R06944043-1.pdf: 710387 bytes, checksum: 04dab9fabcaf5e37e502ed9132874028 (MD5) Previous issue date: 2019 | en |
| dc.description.tableofcontents | Acknowledgments i
Abstract ii List of Figures vi List of Tables vii Chapter 1 Introduction 1 Chapter 2 Related Work 5 2.1 Re-ranking................................. 5 2.2 Stance Classification ........................... 6 Chapter 3 Framework 8 3.1 News Retrieval .............................. 8 3.2 Re-rank .................................. 10 3.2.1 Problem Definition ........................ 10 3.2.2 K-overlap Nearest Neighbors................... 11 3.2.3 K-reciprocal Nearest Neighbors ................. 12 3.2.4 Jaccard Similarity......................... 12 3.2.5 Final Score ............................ 14 3.3 Semi-supervised Multi-task Learning .................. 14 Chapter 4 Experiments 19 4.1 Datasets.................................. 19 4.2 Evaluation and Metric .......................... 21 4.3 Implementation Details.......................... 22 4.4 Results & Analysis 23 Chapter 5 Conclusions 25 Bibliography 26 | |
| dc.language.iso | en | |
| dc.subject | 多任務學習 | zh_TW |
| dc.subject | 重排序 | zh_TW |
| dc.subject | 信息檢索 | zh_TW |
| dc.subject | 立場分析 | zh_TW |
| dc.subject | 自然語言處理 | zh_TW |
| dc.subject | 機器學習 | zh_TW |
| dc.subject | Machine Learning | en |
| dc.subject | Multi-task Learning | en |
| dc.subject | Re-ranking | en |
| dc.subject | Information Retrieval | en |
| dc.subject | Stance Classification | en |
| dc.subject | Natural Language Processing | en |
| dc.title | 基於半監督多任務學習與重排序的立場新聞檢索 | zh_TW |
| dc.title | Semi-supervised Multi-task Learning and Re-ranking for Stance News Retrieval | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 107-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 蔡銘峰(Ming-Feng Tsai),李政德(Cheng-Te Li),葉彌妍(Mi-Yen Yeh) | |
| dc.subject.keyword | 多任務學習,重排序,信息檢索,立場分析,自然語言處理,機器學習, | zh_TW |
| dc.subject.keyword | Multi-task Learning,Re-ranking,Information Retrieval,Stance Classification,Natural Language Processing,Machine Learning, | en |
| dc.relation.page | 30 | |
| dc.identifier.doi | 10.6342/NTU201901795 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2019-07-23 | |
| 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 | |
|---|---|---|---|
| ntu-108-1.pdf 未授權公開取用 | 693.74 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。