簡易檢索 / 詳目顯示

回結果列表
研究生： 程煒倫
Cheng, Wei-Lun
論文名稱： 文句修飾與推薦的輔助寫作系統
Auxiliary writing system based on sentence modification and recommendation
指導教授： 許聞廉
HSU, WEN-LIAN
口試委員: 張詠淳
Chang, Yung-Chun
呂菁菁
LU, CHING-CHING
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 資訊系統與應用研究所
Institute of Information Systems and Applications
論文出版年： 2021
畢業學年度： 109
語文別： 中文
論文頁數： 48
中文關鍵詞： 語意抽取 、搭配詞替換 、中文語句改寫
外文關鍵詞： Semantic Extraction, Collocation Word Replacement, Chinese Sentence Rewriting
相關次數： 點閱：3  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 讓計算機像人類一樣進行中文寫作是相當困難的議題。一來，中文語態和時態上比英文模糊；二來，在詞彙組合上，根據不同語境有其合適的搭配詞組。若直接替換成意義相近的詞彙進行改寫，都容易使句子產生語病謬誤。因此，要能有效傳達完整語意且通順句子的計算機寫作，理解句子結構與詞彙排列都是重要的要素。
    本論文提出一「句子修改輔助系統」，利用替換搭配詞組讓語句更加通順。該方法實現以中心詞為主軸的規則式關係抽取，詳細抽取出句子的主語、謂語、定語、狀語與賓語之訊息。在測試階段，將各自同義詞的所有組合，根據對應依存關係頻率較高者作為系統推薦修改的搭配詞。
    本論文以1000篇聯合報財經新聞，共拆解出5000個複合句提供訓練。實驗結果顯示，動賓關係（VOB）和定中關係（ATT）之詞組推薦分別得到了89.1%和92.8%的精準度。相信對於處理中文語句的句法結構以及搭配詞組替換有很大的幫助，此舉讓計算機在語句寫作上實現更細緻的語意操作。

    It is an essential research topic for computers to write Chinese articles as human beings. Firstly, Passive voice and tense in Chinese are more vague than English. Secondly, there are suitable collocation phrases according to different contexts. If we replace words with their synonyms directly, it is easy to cause the linguistic fallacy. Therefore, understanding sentence structure and vocabulary arrangement are both essential elements to make computers write semantic complete and fluent sentences.
    This thesis proposes a novel "sentence modification auxiliary system" which can supply more suitable collocation to make sentences more fluent. This rule-based relation extraction method is centered on the head word and can extract the information of subject, predicate, attributive, adverbial, and object in the sentence detailedly. In the test phase, all synonym combinations are ranked according to the frequency of the corresponding dependency relationships. These collocation words are the recommended modifications by the system.
    We collect modifications from 1,000 financial news articles which were disassembled to 5,000 compound sentences as a training data set. The experimental results show that the phrase recommendation of the verb-object relationship (VOB) and the attribute relationship (ATT) achieved accuracy of 89.1% and 92.7%, respectively. We believe it could be helpful in the Chinese syntactic structure and Chinese collocation substitution. This allows the computer to achieve more detailed semantic operations in sentence writing.

    摘要i Abstract ii 誌謝iii 1 緒論1 1.1 研究目的與動機. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.1.1 中文自然語言處理的困難點. . . . . . . . . . . . . . . . . . . . . . 1 1.2 研究主題. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 1.3 論文架構. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 2 相關研究5 2.1 中文語意. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 2.1.1 規則式同義詞擴展. . . . . . . . . . . . . . . . . . . . . . . . . . . 5 2.1.2 統計式詞向量. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 2.1.3 搭配詞. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 2.2 句法結構. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 2.2.1 剖析樹. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 2.2.2 句法分析. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 2.2.3 定語. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 2.3 信息抽取. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 2.3.1 開放訊息抽取. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 2.3.2 基於子句的開放信息抽取. . . . . . . . . . . . . . . . . . . . . . . 13 2.4 文本生成. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 2.4.1 句法結構之文本生成. . . . . . . . . . . . . . . . . . . . . . . . . . 14 2.4.2 機率與深度學習之文本生成. . . . . . . . . . . . . . . . . . . . . . 14 3 方法16 3.1 問題敘述. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 3.2 方法概述. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 3.3 依存關係詞組語序定義. . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 3.3.1 依存關係詞組語序. . . . . . . . . . . . . . . . . . . . . . . . . . . 18 3.3.2 主謂賓語的句子骨幹. . . . . . . . . . . . . . . . . . . . . . . . . . 19 3.3.3 修飾詞定語結構. . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 3.4 語句改寫系統. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 3.4.1 同義搭配詞. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 3.4.2 按依存語序進行詞組替換. . . . . . . . . . . . . . . . . . . . . . . 21 4 實驗結果與討論22 4.1 替換詞組資料集. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22 4.2 測試句資料集. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23 4.3 評估方式. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24 4.4 成效評估. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25 5 結論與未來展望27 5.1 結論. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27 5.2 未來展望. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27 參考文獻29 附錄35 A 句子替換依存詞組範例. . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35 B 多依存關係組間的語序範式. . . . . . . . . . . . . . . . . . . . . . . . . . 40 C 抽取子句結構. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 46

    [1] J. Allen, Natural language understanding. Benjamin-Cummings Publishing Co., Inc., 1988.
    [2] E. Reiter and R. Dale, “Building applied natural language generation systems,” Natural Language Engineering, vol. 3, no. 1, pp. 57–87, 1997.
    [3] C. D. Paice, “Constructing literature abstracts by computer: techniques and prospects,” Information Processing & Management, vol. 26, no. 1, pp. 171–186, 1990.
    [4] M. Gambhir and V. Gupta, “Recent automatic text summarization techniques: a survey,” Artificial Intelligence Review, vol. 47, no. 1, pp. 1–66, 2017.
    [5] A. H. Oh and A. I. Rudnicky, “Stochastic natural language generation for spoken dialog systems,” Computer Speech & Language, vol. 16, no. 3-4, pp. 387–407, 2002.
    [6] A. Ratnaparkhi, “Trainable methods for surface natural language generation,” arXiv preprint cs/0006028, 2000.
    [7] G. Angeli, P. Liang, and D. Klein, “A simple domain-independent probabilistic approach to generation,” in Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pp. 502–512, 2010.
    [8] T.-H. Wen, D. Vandyke, N. Mrksic, M. Gasic, L. M. Rojas-Barahona, P.-H. Su, S. Ultes, and S. Young, “A network-based end-to-end trainable task-oriented dialogue system,” arXiv preprint arXiv:1604.04562, 2016.
    [9] N. Mrkšić, D. O. Séaghdha, T.-H. Wen, B. Thomson, and S. Young, “Neural belief tracker: Data-driven dialogue state tracking,” arXiv preprint arXiv:1606.03777, 2016.
    [10] P. F. Brown, J. Cocke, S. A. Della Pietra, V. J. Della Pietra, F. Jelinek, J. Lafferty, R. L. Mercer, and P. S. Roossin, “A statistical approach to machine translation,” Computational linguistics, vol. 16, no. 2, pp. 79–85, 1990.
    [11] P. F. Brown, S. A. Della Pietra, V. J. Della Pietra, and R. L. Mercer, “The mathematics of statistical machine translation: Parameter estimation,” Computational linguistics, vol. 19, no. 2, pp. 263–311, 1993.
    [12] F. J. Och and H. Ney, “Discriminative training and maximum entropy models for statistical machine translation,” in Proceedings of the 40th Annual meeting of the Association for Computational Linguistics, pp. 295–302, 2002.
    [13] W.-Y. Ma and K.-J. Chen, “Introduction to ckip chinese word segmentation system for the first international chinese word segmentation bakeoff,” in Proceedings of the second SIGHAN workshop on Chinese language processing, pp. 168–171, 2003.
    [14] I. Ajzen, “From intentions to actions: A theory of planned behavior,” in Action control, pp. 11–39, Springer, 1985.
    [15] G. Lample, M. Ballesteros, S. Subramanian, K. Kawakami, and C. Dyer, “Neural architectures for named entity recognition,” arXiv preprint arXiv:1603.01360, 2016.
    [16] D. Marcheggiani and I. Titov, “Encoding sentences with graph convolutional networks for semantic role labeling,” arXiv preprint arXiv:1703.04826, 2017.
    [17] M. Stevenson and Y. Wilks, “The interaction of knowledge sources in word sense disambiguation,” Computational Linguistics, vol. 27, no. 3, pp. 321–349, 2001.
    [18] P. Resnik, “A perspective on word sense disambiguation methods and their evaluation,” in Tagging Text with Lexical Semantics: Why, What, and How?, 1997.
    [19] P. Resnik, “Semantic similarity in a taxonomy: An information-based measure and its application to problems of ambiguity in natural language,” Journal of artificial intelligence research, vol. 11, pp. 95–130, 1999.
    [20] M. Davis, The universal computer: The road from Leibniz to Turing. AK Peters/CRC Press, 2018.
    [21] N. Chomsky, Lectures on government and binding: The Pisa lectures. No. 9, Walter de Gruyter, 1993.
    [22] C. Boeckx, Linguistic minimalism: Origins, concepts, methods, and aims. Oxford University Press, 2006.
    [23] S. Ji, S. Pan, E. Cambria, P. Marttinen, and S. Y. Philip, “A survey on knowledge graphs: Representation, acquisition, and applications,” IEEE Transactions on Neural Networks and Learning Systems, 2021.
    [24] E. Agirre and G. Rigau, “Word sense disambiguation using conceptual density,” arXiv preprint cmp-lg/9606007, 1996.
    [25] Z. Dong and Q. Dong, “Hownet-a hybrid language and knowledge resource,” in International Conference on Natural Language Processing and Knowledge Engineering, 2003. Proceedings. 2003, pp. 820–824, IEEE, 2003.
    [26] K.-J. Chen, S.-L. Huang, Y.-Y. Shih, and Y.-J. Chen, “Extended-hownet: A representational framework for concepts,” in Proceedings of OntoLex 2005-Ontologies and Lexical Resources, 2005.
    [27] 梅家驹, 同义詞詞林. 上海辞书出版社, 1983.
    [28] 王鹏, 戴新宇, 陈家骏, and 王启祥, 基于规则的汉语句法分析方法研究. PhD thesis, 2003.
    [29] 何新贵and 彭甫阳, “中文文本的关键词自动抽取和模糊分类,” 中文信息学报, vol. 13, no. 1, pp. 10–16, 1999.
    [30] G. E. Hinton et al., “Learning distributed representations of concepts,” in Proceedings of the eighth annual conference of the cognitive science society, vol. 1, p. 12, Amherst, MA, 1986.

    [31] J. Pennington, R. Socher, and C. D. Manning, “Glove: Global vectors for word representation,” in Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp. 1532–1543, 2014.
    [32] T. Mikolov, K. Chen, G. Corrado, and J. Dean, “Efficient estimation of word representations in vector space,” arXiv preprint arXiv:1301.3781, 2013.
    [33] Y. Bengio, R. Ducharme, P. Vincent, and C. Janvin, “A neural probabilistic language model,” The journal of machine learning research, vol. 3, pp. 1137–1155, 2003.
    [34] A. Mnih and K. Kavukcuoglu, “Learning word embeddings efficiently with noisecontrastive estimation,” in Advances in neural information processing systems, pp. 2265– 2273, 2013.
    [35] F. Smadja, “Retrieving collocations from text: Xtract,” Computational linguistics, vol. 19, no. 1, pp. 143–178, 1993.
    [36] T. J. Osborne, “Tests for constituents: What they really reveal about the nature of syntactic structure,” Language under discussion, vol. 5, no. 1, pp. 1–41, 2018.
    [37] M. A. Fanty, “Context-free parsing with connectionist networks,” in AIP Conference Proceedings, vol. 151, pp. 140–145, American Institute of Physics, 1986.
    [38] J. Li, M.-T. Luong, D. Jurafsky, and E. Hovy, “When are tree structures necessary for deep learning of representations?,” arXiv preprint arXiv:1503.00185, 2015.
    [39] Z. Huang, W. Xu, and K. Yu, “Bidirectional lstm-crf models for sequence tagging,” arXiv preprint arXiv:1508.01991, 2015.
    [40] I. A. Mel’cuk et al., Dependency syntax: theory and practice. SUNY press, 1988.
    [41] I. Sakai, Syntax in universal translation. Her Magesty’s Stationary Office, 1962.
    [42] J.-M. You and K.-J. Chen, “Automatic semantic role assignment for a tree structure,” in Proceedings of the third SIGHAN workshop on chinese language processing, pp. 109–115, 2004.
    [43] R. McDonald, F. Pereira, K. Ribarov, and J. Hajic, “Non-projective dependency parsing using spanning tree algorithms,” in Proceedings of human language technology conference and conference on empirical methods in natural language processing, pp. 523–530, 2005.
    [44] J. D. Choi and A. McCallum, “Transition-based dependency parsing with selectional branching,” in Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1052–1062, 2013.
    [45] C. Dyer, M. Ballesteros, W. Ling, A. Matthews, and N. A. Smith, “Transition-based dependency parsing with stack long short-term memory,” arXiv preprint arXiv:1505.08075, 2015.
    [46] W. Wang and B. Chang, “Graph-based dependency parsing with bidirectional lstm,” in Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2306–2315, 2016.
    [47] T. Dozat and C. D. Manning, “Deep biaffine attention for neural dependency parsing,” arXiv preprint arXiv:1611.01734, 2016.
    [48] T. Dozat and C. D. Manning, “Simpler but more accurate semantic dependency parsing,” arXiv preprint arXiv:1807.01396, 2018.
    [49] Z. Wu, Y. Chen, B. Kao, and Q. Liu, “Perturbed masking: Parameter-free probing for analyzing and interpreting bert,” arXiv preprint arXiv:2004.14786, 2020.
    [50] Y. Cui, W. Che, T. Liu, B. Qin, S. Wang, and G. Hu, “Revisiting pre-trained models for chinese natural language processing,” arXiv preprint arXiv:2004.13922, 2020.
    [51] K. Clark, M.-T. Luong, Q. V. Le, and C. D. Manning, “Electra: Pre-training text encoders as discriminators rather than generators,” arXiv preprint arXiv:2003.10555, 2020.
    [52] W. Che, Y. Feng, L. Qin, and T. Liu, “N-ltp: A open-source neural chinese language technology platform with pretrained models,” arXiv preprint arXiv:2009.11616, 2020.
    [53] W. Che, Z. Li, and T. Liu, “Ltp: A chinese language technology platform,” in Coling 2010: Demonstrations, pp. 13–16, 2010.
    [54] O. Etzioni, M. Banko, S. Soderland, and D. S. Weld, “Open information extraction from the web,” Communications of the ACM, vol. 51, no. 12, pp. 68–74, 2008.
    [55] F. Wu and D. S. Weld, “Open information extraction using wikipedia,” in Proceedings of the 48th annual meeting of the association for computational linguistics, pp. 118–127, 2010.
    [56] M. Schmitz, S. Soderland, R. Bart, O. Etzioni, et al., “Open language learning for information extraction,” in Proceedings of the 2012 joint conference on empirical methods in natural language processing and computational natural language learning, pp. 523–534, 2012.
    [57] A. Fader, S. Soderland, and O. Etzioni, “Identifying relations for open information extraction,” in Proceedings of the 2011 conference on empirical methods in natural language processing, pp. 1535–1545, 2011.
    [58] Y.-H. Tseng, L.-H. Lee, S.-Y. Lin, B.-S. Liao, M.-J. Liu, H.-H. Chen, O. Etzioni, and A. Fader, “Chinese open relation extraction for knowledge acquisition,” in Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, volume 2: Short Papers, pp. 12–16, 2014.
    [59] A. S. White, D. Reisinger, K. Sakaguchi, T. Vieira, S. Zhang, R. Rudinger, K. Rawlins, and B. Van Durme, “Universal decompositional semantics on universal dependencies,” in Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 1713–1723, 2016.
    [60] L. Del Corro and R. Gemulla, “Clausie: clause-based open information extraction,” in Proceedings of the 22nd international conference on World Wide Web, pp. 355–366, 2013.
    [61] G. Angeli, M. J. J. Premkumar, and C. D. Manning, “Leveraging linguistic structure for open domain information extraction,” in Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 344–354, 2015.
    [62] 曹文洁, 宗成庆, and 徐波, “基于中间转换格式的中英文语言生成方法研究,” Journal of Chinese Language and Computing, vol. 14, no. 1, pp. 21–34.
    [63] R. Barzilay and K. R. McKeown, “Sentence fusion for multidocument news summarization,” Computational Linguistics, vol. 31, no. 3, pp. 297–328, 2005.
    [64] Y.-C. Chang, J. S. Chang, H.-J. Chen, and H.-C. Liou, “An automatic collocation writing assistant for taiwanese efl learners: A case of corpus-based nlp technology,” Computer Assisted Language Learning, vol. 21, no. 3, pp. 283–299, 2008.
    [65] C.-B. Huang, C.-L. Liu, W.-T. Kuo, Y.-T. Sun, and M.-H. Lai, “電腦輔助句子重組試題編製(computer assisted test-item generation for sentence reconstruction)[in chinese],” in Proceedings of the 21st Conference on Computational Linguistics and Speech Processing, pp. 165–178, 2009.
    [66] C. D. Manning, M. Surdeanu, J. Bauer, J. R. Finkel, S. Bethard, and D. McClosky, “The stanford corenlp natural language processing toolkit,” in Proceedings of 52nd annual meeting of the association for computational linguistics: system demonstrations, pp. 55–60, 2014.
    [67] C. Manning and H. Schutze, Foundations of statistical natural language processing. MIT press, 1999.
    [68] J. Martin and D. Jurafski, “An introduction to natural language processing, computational linguistics, and speech recognition,” 2000.
    [69] I. Konstas and M. Lapata, “Inducing document plans for concept-to-text generation,” in Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 1503–1514, 2013.
    [70] A. Belz, “Probabilistic generation of weather forecast texts,” in Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Proceedings of the Main Conference, pp. 164–171, 2007.
    [71] E. Reiter, “An architecture for data-to-text systems,” in proceedings of the eleventh European workshop on natural language generation (ENLG 07), pp. 97–104, 2007.
    [72] R. Barzilay and M. Lapata, “Collective content selection for concept-to-text generation,” in Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, pp. 331–338, 2005.
    [73] P. Liang, M. I. Jordan, and D. Klein, “Learning semantic correspondences with less supervision,” in Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP, pp. 91–99, 2009.
    [74] T.-H. Wen, M. Gasic, N. Mrksic, P.-H. Su, D. Vandyke, and S. Young, “Semantically conditioned lstm-based natural language generation for spoken dialogue systems,” arXiv preprint arXiv:1508.01745, 2015.
    [75] R. Lebret, D. Grangier, and M. Auli, “Neural text generation from structured data with application to the biography domain,” arXiv preprint arXiv:1603.07771, 2016.
    [76] D. Bahdanau, K. Cho, and Y. Bengio, “Neural machine translation by jointly learning to align and translate,” arXiv preprint arXiv:1409.0473, 2014.
    [77] H. Mei, M. Bansal, and M. R. Walter, “What to talk about and how? selective generation using lstms with coarse-to-fine alignment,” arXiv preprint arXiv:1509.00838, 2015.
    [78] R. Koncel-Kedziorski, D. Bekal, Y. Luan, M. Lapata, and H. Hajishirzi, “Text generation from knowledge graphs with graph transformers,” arXiv preprint arXiv:1904.02342, 2019.
    [79] 李德堯, “準則式中文句子重組還原,” 國立臺灣大學電機工程學研究所學位論文, 2020.

    QR CODE