請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/71314完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 許永真(Jane Yung-jen Hsu) | |
| dc.contributor.author | Yu-Yan Peng | en |
| dc.contributor.author | 彭于晏 | zh_TW |
| dc.date.accessioned | 2021-06-17T05:04:28Z | - |
| dc.date.available | 2018-07-26 | |
| dc.date.copyright | 2018-07-26 | |
| dc.date.issued | 2018 | |
| dc.date.submitted | 2018-07-23 | |
| dc.identifier.citation | [1] S. Bird. NLTK: the natural language toolkit. In Procedding of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, 2006.
[2] D. Chen, J. Bolton, and C. D. Manning. A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pages 2358–2367, 2016. [3] Y. Cui, T. Liu, Z. Chen, S. Wang, and G. Hu. Consensus Attention-based Neural Networks for Chinese Reading Comprehension. In Proceedings of the 26th International Conference on Computational Linguistics, pages 1777—-1786, Osaka, Japan, 2016. The COLING 2016 Organizing Committee. [4] M. Gardner, J. Grus, M. Neumann, O. Tafjord, P. Dasigi, N. F. Liu, M. Peters, M. Schmitz, and L. S. Zettlemoyer. Allennlp: A deep semantic natural language processing platform. 2017. [5] Y. Gong and S. R. Bowman. Ruminating reader: Reasoning with gated multi-hop attention. CoRR, abs/1704.07415, 2017. [6] 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, pages 1693–1701. Curran Associates, Inc., 2015. [7] U. Hermjakob, A. Echihabi, and D. Marcu. Natural language based reformulation resource and web exploitation for question answering. In Proceedings of The Eleventh Text REtrieval Conference, 2002. [8] F. Hill, A. Bordes, S. Chopra, and J. Weston. The goldilocks principle: Reading children’s books with explicit memory representations. CoRR, abs/1511.02301, 2015. [9] S. Hochreiter and J. Schmidhuber. Long short-term memory. Neural Computation, 9(8):1735–1780, 1997. [10] M. Hu, Y. Peng, and X. Qiu. Mnemonic reader: Machine comprehension with iterative aligning and multi-hop answer pointing. CoRR, abs/1705.02798v2, 2017. [11] R. Jia and P. Liang. Adversarial Examples for Evaluating Reading Comprehension Systems. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2021—-2031, 2017. [12] R. Kadlec, M. Schmid, O. Bajgar, and J. Kleindienst. Text Understanding with the Attention Sum Reader Network. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 2016. [13] M. Kaszkiel and J. Zobel. Passage retrieval revisited. In Proceedings of the 20th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 178–185, 1997. [14] Y. Kim. Convolutional Neural Networks for Sentence Classification. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, pages 1746–1751, 2014. [15] D. P. Kingma and J. Ba. Adam: A Method for Stochastic Optimization. In Proceeding of the 3rd International Conference for Learning Representations, 2015. [16] K. Lee, S. Salant, T. Kwiatkowski, A. Parikh, D. Das, and J. Berant. Learning recurrent span representations for extractive question answering. CoRR, abs/1611.01436, 2016. [17] R. Liu, J. Hu, W. Wei, Z. Yang, and E. Nyberg. Structural Embedding of Syntactic Trees for Machine Comprehension. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 815–824, 2017. [18] T. Luong, H. Pham, and C. D. Manning. Effective Approaches to Attention-based Neural Machine Translation. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 1412–1421, 2015. [19] T. Onishi, H. Wang, M. Bansal, K. Gimpel, and D. McAllester. Who did What: A Large-Scale Person-Centered Cloze Dataset. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2230–2235, 2016. [20] J. Pennington, R. Socher, and C. Manning. Glove: Global Vectors for Word Representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, pages 1532–1543, 2014. [21] J. Prager, E. Brown, A. Coden, and D. Radev. Question-answering by predictive annotation. In Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval, pages 184–191, 2000. [22] P. Rajpurkar, J. Zhang, K. Lopyrev, and P. Liang. SQuAD: 100,000+ Questions for Machine Comprehension of Text. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2383–2392, Stroudsburg, PA, USA, June 2016. Association for Computational Linguistics. [23] A. H. Ralph Weischedel, Martha Palmer, Mitchell Marcus, Eduard Hovy, Sameer Pradhan, Lance Ramshaw, Nianwen Xue, Ann Taylor, Jeff Kaufman, Michelle Franchini, Mohammed El-Bachouti, Robert Belvin. OntoNotes Release 5.0 LDC2013T19. Linguistic Data Consortium, 2013. [24] M. Richardson, C. J. C. Burges, and E. Renshaw. MCTest: A Challenge Dataset for the Open-Domain Machine Comprehension of Text. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 193–203, October 2013. [25] S. Robertson, S. Walker, M. M. Beaulieu, M. Gatford, and A. Payne. Okapi at TREC-4. In Proceedings of The Fourth Text REtrieval Conference, 1995. [26] S. Robertson, S. Walker, S. Jones, M. Hancock-Beaulieu, and M. Gatford. Okapi at TREC-3. In Proceedings of The Third Text REtrieval Conference, pages 109–126, 1994. [27] M. Schuster and K. Paliwal. Bidirectional recurrent neural networks. IEEE Transactions on Signal Processing, 45(11):2673–2681, 1997. [28] M. Seo, A. Kembhavi, A. Farhadi, and H. Hajishirzi. Bidirectional Attention Flow for Machine Comprehension. In Proceeding of the 5th International Conference on Learning Representations, 2017. [29] Y. Shen, P.-S. Huang, J. Gao, and W. Chen. ReasoNet: Learning to Stop Reading in Machine Comprehension. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 1047–1055, 2017. [30] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov. Dropout: A Simple Way to Prevent Neural Networks from Overfitting. Journal of Machine Learning Research, 15:1929–1958, 2014. [31] R. K. Srivastava, K. Greff, and J. Schmidhuber. Highway networks. CoRR, abs/1505.00387, 2015. [32] S. Tellex, B. Katz, J. Lin, A. Fernandes, and G. Marton. Quantitative evaluation of passage retrieval algorithms for question answering. In Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval, pages 41–47, 2003. [33] S. Wang and J. Jiang. Machine comprehension using match-lstm and answer pointer. CoRR, abs/1608.07905, 2016. [34] W. Wang, N. Yang, F. Wei, B. Chang, and M. Zhou. Gated Self-Matching Networks for Reading Comprehension and Question Answering. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pages 189–198, 2017. [35] Z. Wang, H. Mi, W. Hamza, and R. Florian. Multi-perspective context matching for machine comprehension. CoRR, abs/1612.04211, 2016. [36] Y. Yu, W. Zhang, K. Hasan, M. Yu, B. Xiang, and B. Zhou. End-to-end reading comprehension with dynamic answer chunk ranking. CoRR, abs/1610.09996, 2016. [37] J. Zhang, X. Zhu, Q. Chen, L. Dai, S. Wei, and H. Jiang. Exploring question understanding and adaptation in neural-network-based question answering. CoRR, abs/1703.04617, 2017. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/71314 | - |
| dc.description.abstract | 機器閱讀理解問題目的是從文章中抽取重要的資訊回答相關的問題。雖然有很多方法被提出，相似性干擾問題仍未被解決。相似性干擾問題指因為某些文章中的句子不包含答案卻跟問題很相似引起的錯誤。命名實體具有的獨特性可以用來區分這些相似的句子，讓模型不會遭受這些句子的干擾。在本論文中提出了命名實體過濾器。命名實體過濾器能善加利用命名實體所擁有的資訊減緩相似性干擾問題。論文中的實驗結果顯示命名實體過濾器能夠提升模型的穩健性，不減少SQuAD 上的 F1 分數，得到在兩個對抗式資料集 5% 到 10% F1 分數的提升。同時命名實體過濾器也能夠只損失不到 1% 原始資料集的 F1 分數簡單地提升其他現有的模型在對抗式資料集 5% F1 分數。 | zh_TW |
| dc.description.abstract | The machine reading comprehension problem aims to extract crucial information from the given document to answer the relevant questions.Although many methods regarding the problem have been proposed, the similarity distraction problem inside remains unsolved.The similarity distraction problem addresses the error caused by some sentences being very similar to the question but not containing the answer.Named entities have the uniqueness which can be utilized to distinguish similar sentences to prevent models from being distracted.In the thesis, named entity filters (NE filters) are proposed. NE filters can utilize the information of named entities to alleviate the similarity distraction problem.Experiment results in the thesis show that the NE filter can enhance the robustness of the used model. It increases 5% to 10% F1 score on two adversarial SQuAD datasets without decreasing the F1 score on the original SQuAD dataset.Besides, the NE filter easily increases 5% F1 score of other existing models on the adversarial datasets with less than 1% loss on the original one. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-17T05:04:28Z (GMT). No. of bitstreams: 1 ntu-107-R04944002-1.pdf: 911021 bytes, checksum: 9bc9013a9c0fb08e8a111279ea2853f7 (MD5) Previous issue date: 2018 | en |
| dc.description.tableofcontents | 誌謝 iii
摘要 v Abstract vii 1 Introduction 1 1.1 Background 1 1.2 Motivation 3 1.3 Thesis Structure 4 2 Literature Review 5 2.1 Machine Reading Comprehension 5 2.2 Answering Passage Retrieval 7 2.3 Attention-Based Neural Network Models 8 3 Machine Reading Comprehension 11 3.1 Problem Definition 11 3.2 Similarity Distraction 12 3.3 Proposed Solution 13 4 Named Entity Filters 15 4.1 The Baseline Attention-based Model 15 4.2 Implementation 19 4.3 Append to Existing Models 20 5 Experiments 23 5.1 Datasets 23 5.1.1 The Stanford Question Answering Dataset 23 5.1.2 Adversarial SQuAD Datasets 24 5.2 Experimental Settings 25 5.3 Results 25 5.3.1 Evaluation Scores 25 5.3.2 Examples 28 5.3.3 Cooperation with Other Models 31 5.4 Discussions 35 5.4.1 Problems of Similarity 35 5.4.2 Usefulness of Named Entities 35 5.4.3 Different Weights in NE Filters 36 5.4.4 Degenerated NE Filters 37 5.4.5 Training With NE Filters 40 5.4.6 Errors from NE Filters 40 6 Conclusion 43 Bibliography 45 | |
| dc.language.iso | en | |
| dc.subject | 注意力機制 | zh_TW |
| dc.subject | 穩健性 | zh_TW |
| dc.subject | 類神經網路 | zh_TW |
| dc.subject | 命名實體 | zh_TW |
| dc.subject | 相似度 | zh_TW |
| dc.subject | Attention mechanism | en |
| dc.subject | Named entity | en |
| dc.subject | Neural networks | en |
| dc.subject | Robustness | en |
| dc.subject | Similarity | en |
| dc.title | 命名實體過濾器使用於穩健的機器閱讀理解 | zh_TW |
| dc.title | Named Entity Filters for Robust Machine Reading Comprehension | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 106-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 黃乾綱(Chien-Kang Huang),蔡宗翰(Richard Tzong-Han Tsai),古倫維(Lun-Wei Ku),馬偉雲(Wei-Yun Ma) | |
| dc.subject.keyword | 注意力機制,命名實體,類神經網路,穩健性,相似度, | zh_TW |
| dc.subject.keyword | Attention mechanism,Named entity,Neural networks,Robustness,Similarity, | en |
| dc.relation.page | 49 | |
| dc.identifier.doi | 10.6342/NTU201801153 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2018-07-23 | |
| 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-107-1.pdf 未授權公開取用 | 889.67 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。