請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/69582
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 | Chieh-Teng Chang | en |
dc.contributor.author | 張介騰 | zh_TW |
dc.date.accessioned | 2021-06-17T03:20:03Z | - |
dc.date.available | 2018-06-29 | |
dc.date.copyright | 2018-06-29 | |
dc.date.issued | 2018 | |
dc.date.submitted | 2018-06-26 | |
dc.identifier.citation | [1] Ayana, S. Shen, Z. Liu, and M. Sun. Neural headline generation with minimum risk training. arXiv preprint arXiv:1604.01904, 2016.
[2] D. Bahdanau, K. Cho, and Y. Bengio. Neural machine translation by jointly learning to align and translate. In ICLR, 2014. [3] M.Banko,V.O.Mittal,andM.J.Witbrock.Headlinegenerationbasedonstatistical translation. In ACL, pages 318–325, 2000. [4] G. Bradski. The OpenCV Library. Dr. Dobb’s Journal of Software Tools, 2000. [5] Q. Chen, X. Zhu, Z. Ling, S. Wei, and H. Jiang. Distraction-based neural networks for modeling documents. In IJCAI, pages 2754–2760, 2016. [6] J. Cheng and M. Lapata. Neural summarization by extracting sentences and words. In ACL, pages 484–494, 2016. [7] T. Cohn and M. Lapata. Sentence compression beyond word deletion. In COLING, pages 137–144, 2008. [8] J. Duchi, E. Hazan, and Y. Singer. Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research, 12:2121–2159, 2011. [9] H. P. Edmundson. New methods in automatic extracting. J. ACM, pages 264–285, 1969. [10] G. Erkan and D. R. Radev. LexRank: Graph-based lexical centrality as salience in text summarization. Journal of Artificial Intelligence Research, 22:457–479, 2004. [11] K. Filippova, E. Alfonseca, C. A. Colmenares, L. Kaiser, and O. Vinyals. Sentence compression by deletion with LSTMs. In EMNLP, pages 360–368, 2015. [12] M. Gambhir and V. Gupta. Recent automatic text summarization techniques: A survey. Artificial Intelligence Review, 47(1):1–66, 2017. [13] Gehring, Jonas, and Auli, Michael and Grangier, David and Dauphin, Yann N. A convolutional encoder model for neural machine translation. ACL, 2017. [14] Gehring, Jonas, and Auli, Michael and Grangier, David and Yarats, Denis and Dauphin, Yann N. Convolutional sequence to sequence learning. ICML, 2017. [15] D. Graff and K. Chen. Chinese Gigaword, 2003. Linguistic Data Consortium. [16] J.Gum,Z.Lu,H.Li,andV.O.K.Li.Incorporatingcopyingmechanisminsequence-to-sequence learning. In ACL, pages 1631–1640, 2016. [17] W. C. Hannas. Asia’s orthographic dilemma. University of Hawaii Press, 1997. [18] B.Hu,Q.Chen,andF.Zhu.LCSTS:AlargescaleChineseshorttextsummarization dataset. In EMNLP, pages 1967–1972, 2015. [19] S.Jean,K.Cho,R.Memisevic,andY.Bengio.Onusingverylargetargetvocabulary for neural machine translation. arXiv preprint arXiv:1412.2007, 2014. [20] G. Klein, Y. Kim, Y. Deng, J. Senellart, and A. M. Rush. OpenNMT: Open-source toolkit for neural machine translation. In ACL, pages 67–72, 2017. [21] K. Knight and D. Marcu. Statistics-based summarization-step one: Sentence compression. In AAAI/IAAI, pages 703–710, 2000. [22] P. Li, L. Bing, and W. Lam. Actor-critic based training framework for abstractive summarization. arXiv preprint arXiv:1803.11070, 2018. [23] P. Li, W. Lam, L. Bing, and Z. Wang. Deep recurrent generative decoder for abstrac- tive text summarization. In EMNLP, pages 2091–2100, 2017. [24] C.-Y. Lin. ROUGE: A package for automatic evaluation of summaries. In Proceed- ings of the ACL-04 Workshop, pages 74–81, 2004. [25] H. P. Luhn. The automatic creation of literature abstracts. IBM Journal of research and development, 2(2):159–165, 1958. [26] M.-T. Luong, H. Pham, and C. D. Manning. Effective approaches to attention-based neural machine translation. In EMNLP, 2015. [27] S. Ma, X. Sun, W. Li, S. Li, W. Li, and X. Ren. Word embedding attention network: Generating words by querying distributed word representations for paraphrase gen- eration. In NAACL HLT, 2018. [28] R. Mihalcea and P. Tarau. TextRank: Bringing order into text. In EMNLP, 2004. [29] R. Nallapati, B. Zhou, C. Gulcehre, B. Xiang, et al. Abstractive text summarization using sequence-to-sequence RNNs and beyond. In SIGNLL, pages 280–290, 2016. [30] A. M. Rush, S. Chopra, and J. Weston. A neural attention model for abstractive sentence summarization. In EMNLP, pages 379–389, 2015. [31] I. Sutskever, O. Vinyals, and Q. V. Le. Sequence to sequence learning with neural networks. In NIPS, pages 3104–3112, 2014. [32] J.-M. Torres-Moreno. Automatic Text Summarization. John Wiley & Sons, Inc., 2014. [33] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin. Attention is all you need. In NIPS, pages 6000–6010, 2017. [34] Y.Wu,M.Schuster,Z.Chen,Q.V.Le,M.Norouzi,W.Macherey,M.Krikun,Y.Cao, Q. Gao, K. Macherey, et al. Google’s neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144, 2016. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/69582 | - |
dc.description.abstract | 自動抽象文本摘要是自然語言處理的一個重要且充滿挑戰性的研究課題。在許多廣泛使用的語言中,中文具有特殊的語言性質,即中文的字包含著與詞相當的豐富信息。現有的中文文本摘要方法不是完全採用基於字就是完全採用基於詞的表示方法,未能充分利用這兩種表示方法所攜帶的信息。為了準確地捕捉文章的本質,我們提出了一個基於字與詞混用的方法(HWC),保留了基於字與基於詞表示方法的優點。我們將其應用於兩種現有的架構來評估所提出的HWC 方法的優勢。發現其在廣泛使用的資料集LCSTS 上產生超越目前最先進的方法24 個ROUGE 百分點。除此之外,我們發現LCSTS 資料集中包含一個問題,並提供一個腳本來刪除重疊的資料對(摘要和簡短文本)。以便為社群創建一個乾淨的資料集。提出的HWC 方法也在新的、乾淨的LCSTS 資料集上產生了最佳的表現結果。 | zh_TW |
dc.description.abstract | Automatic abstractive text summarization is an important and challeng- ing research topic of natural language processing. Among many widely used languages, the Chinese language has a special property that a Chinese char- acter contains rich information comparable to a word. Existing Chinese text summarization methods, either adopt totally character-based or word-based representations, fail to fully exploit the information carried by both repre- sentations. To accurately capture the essence of articles, we propose a hy- brid word-character approach (HWC) which preserves the advantages of both word-based and character-based representations. We evaluate the advantage of the proposed HWC approach by applying it to two existing methods, and discover that it generates state-of-the-art performance with a margin of 24 ROUGE points on a widely used dataset LCSTS. In addition, we find an is- sue contained in the LCSTS dataset and offer a script to remove overlapping pairs (a summary and a short text) to create a clean dataset for the commu- nity. The proposed HWC approach also generates the best performance on the new, clean LCSTS dataset. | en |
dc.description.provenance | Made available in DSpace on 2021-06-17T03:20:03Z (GMT). No. of bitstreams: 1 ntu-107-R05944007-1.pdf: 694474 bytes, checksum: 21abf4351f0dfd96e486ae0ec36a3af8 (MD5) Previous issue date: 2018 | en |
dc.description.tableofcontents | 口試委員會審定書 iii
摘要 v Abstract vii 1 Introduction 1 1.1 Motivation.................................. 1 1.2 Proposed Method .............................. 3 1.3 Outline of the Thesis ............................ 3 2 Literature Review 5 2.1 Extractive and Abstractive Summarization........................ 5 2.2 Chinese Text Summarization Datasaet ................... 5 2.3 Open-source Implementation........................ 6 2.4 Machine Translation ............................ 6 3 Problem Definition 9 3.0.1 SymbolTable............................ 9 4 Methodology 11 4.1 Encoder-Decoder Frameworks ....................... 12 4.1.1 Attentional Seq2seq ........................ 12 4.1.2 Transformer............................. 12 4.1.3 Training............................... 13 4.2 Hybrid Word-Character Approach ..................... 14 5 Experiments 17 5.1 Experimental Setup............................. 17 5.1.1 Dataset ............................... 18 5.1.2 Evaluation Metrics ......................... 20 5.2 Compared Methods............................. 21 5.3 Preprocessing and Hyperparameters .................... 22 5.4 Results and Discussion ........................... 26 5.4.1 Vocabulary size........................... 27 5.4.2 The effects of the HWC approach ................. 27 5.4.3 Analysis of generated summaries ................. 28 5.4.4 Training time............................ 31 6 Conclusion 33 6.1 Summary and Contribution......................... 33 6.2 Future Studies................................ 34 Bibliography 35 | |
dc.language.iso | en | |
dc.title | 基於字與詞混合方法之抽象摘要研究 | zh_TW |
dc.title | A Hybrid Word-Character Approach to Abstractive Summarization | en |
dc.type | Thesis | |
dc.date.schoolyear | 106-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 李琳山(Lin-Shan Lee),李宏毅(Hung-yi Lee),吳昇(Sun Wu),古倫維(Lun-Wei Ku) | |
dc.subject.keyword | 抽象摘要,類神經網路,自然語言處理,編碼器-解碼器架構, | zh_TW |
dc.subject.keyword | Abstractive Summarization,Neural Networks,Natural Language Processing,Encoder-Decoder Framework, | en |
dc.relation.page | 38 | |
dc.identifier.doi | 10.6342/NTU201801093 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2018-06-26 | |
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 目前未授權公開取用 | 678.2 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。