Please use this identifier to cite or link to this item:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/86412Full metadata record
| ???org.dspace.app.webui.jsptag.ItemTag.dcfield??? | Value | Language |
|---|---|---|
| dc.contributor.advisor | 謝舒凱(Shu-Kai Hsieh) | |
| dc.contributor.author | Cing-Fang Shih | en |
| dc.contributor.author | 石晴方 | zh_TW |
| dc.date.accessioned | 2023-03-19T23:54:19Z | - |
| dc.date.copyright | 2022-08-24 | |
| dc.date.issued | 2022 | |
| dc.date.submitted | 2022-08-22 | |
| dc.identifier.citation | Bayes, T. (1763). LII. An essay towards solving a problem in the doctrine of chances. By the late Rev. Mr. Bayes, FRS communicated by Mr. Price, in a letter to John Canton, AMFR S [Publisher: The Royal Society London]. Philosophical transactions of the Royal Society of London, (53), 370–418. Bybee, J. (1995). Regular morphology and the lexicon [Publisher: Taylor & Francis]. Language and cognitive processes, 10(5), 425–455. Bybee, J. (2006). From usage to grammar: The mind’s response to repetition [Publisher: JSTOR]. Language, 711–733. Bybee, J. (2013). Usage-based theory and exemplar representations of constructions. The Oxford handbook of construction grammar. Chan, Y. S., Ng, H. T., & Chiang, D. (2007). Word sense disambiguation improves statistical machine translation. Proceedings of the 45th annual meeting of the association of computational linguistics, 33–40. Chaplot, D. S., & Salakhutdinov, R. (2018). Knowledge-based word sense disambiguation using topic models. Proceedings of the AAAI conference on artificial intelligence, 32(1). Chen, A. C.-H. (2020). Words, constructions and corpora: network representations of constructional semantics for mandarin space particles. Corpus Linguistics and Linguistic Theory. Cheng, L. L., & Huang, C. (1996). Two types of donkey sentences. Natural Language Semantics, 4(2), 121–163. Cohen, J. (1960). A coefficient of agreement for nominal scales [Publisher: Sage Publications Sage CA: Thousand Oaks, CA]. Educational and psychological measurement, 20(1), 37–46. Crammer, K., & Singer, Y. (2001). On the algorithmic implementation of multiclass kernel-based vector machines. Journal of machine learning research, 2(Dec), 265–292. Croft, W. (2001). Radical construction grammar: Syntactic theory in typological perspective. Oxford University Press on Demand. Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 . Dunn, J. (2017). Computational learning of construction grammars [Publisher: Cambridge University Press]. Language and cognition, 9(2), 254–292. Erman, B., & Warren, B. (2000). The idiom principle and the open choice principle [Publisher: De Gruyter]. Text & Talk, 20(1), 29–62. Evans, V. (2005). The meaning of time: polysemy, the lexicon and conceptual structure. Journal of linguistics, 41(1), 33–75. Fellbaum, C. (2010). Wordnet. Theory and applications of ontology: computer applications (pp. 231–243). Springer. Fillmore, C. J. (1988). The mechanisms of” construction grammar”. Annual Meeting of the Berkeley Linguistics Society, 14, 35–55. Fillmore, C. J., Kay, P., & O’connor, M. C. (1988). Regularity and idiomaticity in grammatical constructions: The case of let alone [Publisher: JSTOR]. Language, 501–538. Gibbs, R. W., & Matlock, T. (2001). Psycholinguistic perspectives on polysemy. AMSTERDAM STUDIES IN THE THEORY AND HISTORY OF LINGUISTIC SCIENCE SERIES 4, 213–240. Goldberg, A. E. (1995). Constructions: A construction grammar approach to argument structure. University of Chicago Press. Goldberg, A. E. (2006). Constructions at work: The nature of generalization in language. Oxford University Press on Demand. Goldberg, A. E. (2019). Explain Me This. Princeton University Press. Gries, S. T. (2015). More (old and new) misunderstandings of collostructional anal- ysis: On Schmid and Küchenhoff (2013) [Publisher: De Gruyter]. Cognitive Linguistics, 26(3), 505–536. Gries, S. T., & Stefanowitsch, A. (2004). Co-varying collexemes in the into-causative [Publisher: CSLI Stanford, CA]. Language, culture, and mind, 225–236. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735–1780. Huang, C.-R., & Hsieh, S.-K. (2010). Infrastructure for cross-lingual knowledge representation-towards multilingualism in linguistic studies. Taiwan NSC-granted Research Project (NSC 96-2411-H-003-061-MY3). Huang, C.-R., Hsieh, S.-K., Hong, J.-F., Chen, Y.-Z., Su, I.-L., Chen, Y.-X., & Huang, S.-W. (2010). Chinese Wordnet: Design, implementation, and application of an infrastructure for cross-lingual knowledge processing. Journal of Chinese Information Processing, 24(2), 14–23. Hung, C., & Chen, S.-J. (2016). Word sense disambiguation based sentiment lexicons for sentiment classification [Publisher: Elsevier]. Knowledge-Based Systems, 110, 224–232. Hung, S. H. (2021). Manual action motivates networked meanings of a productive construction in mandarin: rethinking polysemy. Chinese Language and Discourse, 12(2), 215–237. Jackendoff, R. S. (1985). Semantics and cognition (Vol. 8). MIT press. Joulin, A., Grave, E., Bojanowski, P., & Mikolov, T. (2016). Bag of tricks for efficient text classification. arXiv preprint arXiv:1607.01759. Lakoff, G. (1987). Women, fire, and dangerous things: what categories reveal about the mind. University of Chicago press. Langacker, R. (1988). A usage-based model. Topics in cognitive linguistics (p. 127). John Benjamins. Langacker, R. (2000). A dynamic usage-based model [Publisher: csli Publications]. Usage based models of language, 1–64. Langacker, R. W. (1987). Foundations of cognitive grammar: theoretical prerequisites (Vol. 1). Stanford university press. Lee, Y. K., & Ng, H. T. (2002). An empirical evaluation of knowledge sources and learning algorithms for word sense disambiguation. Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing (EMNLP 2002), 41–48. Liu, T.-J. (2014). PTT Corpus: Construction and Applications (Master’s thesis). National Taiwan University. Lu, C., Tsai, I.-N., Su, I.-W., & Liu, T.-H. (2018). Internal structures and constructional meanings`: Da-X-da-Y' and its related constructions in mandarin Chinese. Workshop on Chinese Lexical Semantics, 91–106. Madabushi, H. T., Romain, L., Divjak, D., & Milin, P. (2020). CxGBERT: BERT meets Construction Grammar. arXiv preprint arXiv:2011.04134. Miller, G. A. (1995). Wordnet: a lexical database for english. Communications of the ACM, 38(11), 39–41. Pedersen, T. (1996). Fishing for exactness. arXiv preprint cmp-lg/9608010. Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., et al. (2011). Scikit- learn: Machine learning in Python [Publisher: JMLR. org]. the Journal of machine Learning research, 12, 2825–2830. Ramakrishnan, G., Jadhav, A., Joshi, A., Chakrabarti, S., & Bhattacharyya, P. (2003). Question answering via Bayesian inference on lexical relations. Proceedings of the ACL 2003 workshop on Multilingual summarization and question answering, 1–10. Ravin, Y., & Leacock, C. (2000). Polysemy: an overview. Polysemy: Theoretical and computational approaches, 1–29. Stefanowitsch, A., & Gries, S. T. (2003). Collostructions: Investigating the Interaction of Words and Constructions [Publisher: John Benjamins Type: Journal Article]. International Journal of Corpus Linguistics, 8(2), 209–243. Stefanowitsch, A., & Gries, S. T. (2005). Covarying Collexemes [Publisher: De Gruyter Mouton]. Corpus linguistics and linguistic theory, 1(1), 1–43. Su, I.-W. (2002). Why a construction-that is the question! Concentric: Studies in Linguistics, 28(2), 27–42. Taylor, J. R. (2003). Linguistic categorization. OUP Oxford. Tomasello, M. (2005). Constructing a language: A usage-based theory of language acquisition. Harvard university press. Torre, E. (2017). Concerning the notion of constructional polysemy. Poster presented at the 23rd Architectures and Mechanisms of Language Processing Conference, Lancaster, UK. Tseng, Y.-H., Shih, C.-F., Chen, P.-E., Chou, H.-Y., Ku, M.-C., & Hsieh, S.-K. (2022). CxLM: A Construction and Context-aware Language Model. Proceedings of the 13th Language Resources and Evaluation Conference. Tsou, B. K. (2012). Idiomaticity and classical traditions in some east asian languages. Proceedings of the 26th Pacific Asia Conference on Language, Information, and Computation, 39–55. Verhagen, A. (2002). From parts to wholes and back again [Publisher: Walter de Gruyter GmbH & Co. KG Berlin, Germany]. Vylomova, E., Rimell, L., Cohn, T., & Baldwin, T. (2015). Take and took, gaggle and goose, book and read: evaluating the utility of vector differences for lexical relation learning. arXiv preprint arXiv:1509.01692. Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., et al. (2020). Transformers: state-of- the-art natural language processing. Proceedings of the 2020 conference on empirical methods in natural language processing: system demonstrations, 38–45. Yuan, D., Richardson, J., Doherty, R., Evans, C., & Altendorf, E. (2016). Semi- supervised word sense disambiguation with neural models. arXiv preprint arXiv:1603.07012. Zhan, W. (2017). Some Key Issues on Building A Knowledge Database of Chinese Constructions. Journal of Chinese Information Processing, 31(1), 230–238. Zhong, Z., & Ng, H. T. (2012). Word sense disambiguation improves information retrieval. Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 273–282. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/86412 | - |
| dc.description.abstract | 由多義引起的語義歧義常阻礙機器對於人類語言的理解。因此，詞義消歧（WSD）一直是自然語言處理中重要的任務。除了字詞，作為形式-意義配對的構式同樣具有多義特徵。本論文旨在將詞義消歧任務從單詞層次擴展到構式層次，並利用語料庫與計算語言學方法研究構式的多義性。為了了解空槽和構式之間的相互作用，我們運用搭配分析（collostruction analysis）將兩者的吸引程度進行量化。隨後，本研究鎖定十二個多義構式，並標記構式中兩個空槽間的語義關係。透過標記資料，我們分析了空槽間語義關係與構式語義的配對。最後，本研究使用 3×2 因素之實驗設計，以探討各模型預測空槽間語義關係之能力。研究結果顯示，模型能夠區分空槽間的語義關係，代表其具有分類構式語義的能力。在本論文中，帶有弱監督線索的 BERT 模型可以達到 80% 的預測準確度，說明弱監督線索和上下文脈絡有助於提高預測構式語義的準確度。 | zh_TW |
| dc.description.abstract | Semantic ambiguity arising from polysemy has hindered the machine from thoroughly understanding human language. Thus, Word Sense Disambiguation (WSD) has always been a significant task in natural language processing. Similar to words, constructions, which are conventionalized form-meaning pairings, also possess the polysemous trait. Therefore, this thesis aims to extend the disambiguation task from word-level to construction-level. This thesis investigated the polysemy of constructions with corpus-based and computational approaches. To understand the interaction between slots and constructions, a collostruction analysis was conducted. Subsequently, examples of 12 potentially polysemous construction forms were annotated with the semantic relation between two open slots X and Y. Afterwards, the mapping between X/Y relations and construction senses was examined directly from the annotated data. Finally, a 3×2 experiment was employed to investigate the predictive abilities of X/Y relations of different models. The results showed that models could distinguish between X/Y relations, which implied that models could classify the construction senses. The best performance was achieved by BERT with weak supervision signals, reaching an accuracy of 0.8. It can be concluded that weak supervision signals and contextual information can help enhance prediction accuracy. | en |
| dc.description.provenance | Made available in DSpace on 2023-03-19T23:54:19Z (GMT). No. of bitstreams: 1 U0001-2208202200052700.pdf: 3214289 bytes, checksum: 4ac81a1570ce3fb86a652db069914d49 (MD5) Previous issue date: 2022 | en |
| dc.description.tableofcontents | 論文口試委員審定書 i 致謝 iii 摘要 v Abstract vii List of Figures ix List of Tables xi 1 Introduction 1 1.1 Background................................ 1 1.2 Motivation................................. 2 1.3 Research Purposes ............................ 3 1.4 Organization ............................... 4 2 Literature Review 5 2.1 The Usage-based Constructionist Approach . . . . . . . . . . . . . . 5 2.2 Constructional Polysemy in Mandarin Chinese . . . . . . . . . . . . . 8 2.3 Computational Approaches in CxG Studies . . . . . . . . . . . . . . 14 3 Data Collection 17 3.1 Construction Database.......................... 18 3.2 CorpusData ............................... 19 3.3 Construction Matches Extraction .................... 19 3.4 Co-varying Collexeme Analysis ..................... 21 3.4.1 Computing Methods ....................... 21 3.4.2 Results and Interpretation.................... 23 4 Data Annotation and Analysis 27 4.1 X/Y Relation Annotation ........................ 27 4.2 AnnotationResults............................ 30 4.3 Construction Sense Analysis....................... 33 5 Classification Models 41 5.1 Experimental Design ........................... 41 5.1.1 Baseline Models ......................... 42 5.1.2 Word Embedding Models .................... 44 5.2 Model Evaluation............................. 47 5.2.1 Baseline Models ......................... 47 5.2.2 Word Embedding Models .................... 48 5.2.3 Comparison of Model Performance ............... 50 5.3 Error Analysis............................... 52 6 Conclusion 55 6.1 Summary ................................. 55 6.2 Research Limitations........................... 56 6.3 FutureWorks............................... 56 Appendix A Four-word Structures of Reduplication in CCCD 59 Appendix B Definitions of Semantic Relations 61 References 65 | |
| dc.language.iso | en | |
| dc.subject | 詞嵌入 | zh_TW |
| dc.subject | 構式語義 | zh_TW |
| dc.subject | 一詞多義 | zh_TW |
| dc.subject | 分類模型 | zh_TW |
| dc.subject | 一詞多義 | zh_TW |
| dc.subject | 構式語法 | zh_TW |
| dc.subject | 分類模型 | zh_TW |
| dc.subject | 詞嵌入 | zh_TW |
| dc.subject | 構式語義 | zh_TW |
| dc.subject | 構式語法 | zh_TW |
| dc.subject | word embeddings | en |
| dc.subject | construction sense | en |
| dc.subject | polysemy | en |
| dc.subject | construction sense | en |
| dc.subject | word embeddings | en |
| dc.subject | classification model | en |
| dc.subject | Construction Grammar | en |
| dc.subject | polysemy | en |
| dc.subject | classification model | en |
| dc.subject | Construction Grammar | en |
| dc.title | 漢語構式語意自動分類研究 | zh_TW |
| dc.title | Semantic Classification of Mandarin Chinese Constructions | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 110-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 陳正賢(Cheng-Hsien Chen),張瑜芸(Yu-Yun Chang) | |
| dc.subject.keyword | 構式語法,一詞多義,構式語義,詞嵌入,分類模型, | zh_TW |
| dc.subject.keyword | Construction Grammar,polysemy,construction sense,word embeddings,classification model, | en |
| dc.relation.page | 70 | |
| dc.identifier.doi | 10.6342/NTU202202624 | |
| dc.rights.note | 同意授權(全球公開) | |
| dc.date.accepted | 2022-08-22 | |
| dc.contributor.author-college | 文學院 | zh_TW |
| dc.contributor.author-dept | 語言學研究所 | zh_TW |
| dc.date.embargo-lift | 2022-08-24 | - |
| Appears in Collections: | 語言學研究所 | |
Files in This Item:
| File | Size | Format | |
|---|---|---|---|
| U0001-2208202200052700.pdf | 3.14 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.