1. NCCU Academic Hub
  2. 學術產出
  3. College of Foreign Languages and Literature
  4. Theses
  5. Item

學術產出-Theses

Article View/Open

Publication Export

Google ScholarTM

政大圖書館

Citation Infomation

  • No doi shows Citation Infomation
題名 多義詞詞性分辨模型的訓練資料準備與前處理: 以臺灣客語「个」為例
Preparation and Preprocessing of Training Data for Word Sense Disambiguation Model: A Case Study of Taiwan Hakka Polysemy GE
作者 陳彥宏
Chen, Yanhong
貢獻者 賴惠玲
Lai, Hui-Ling
陳彥宏
Chen, Yanhong
關鍵詞 臺灣客語
多義詞詞意分辨
深度學習
資料標記
Taiwan Hakka
Word sense disambiguation
Deep learning
Data annotation
日期 2023
上傳時間 2-Jun-2023 11:33:41 (UTC+8)
摘要 Lai(2022)在訓練臺灣客家語料庫中「个」詞的多義詞詞意分辨模型時，參考了過去的「个」的研究(賴文英, 2012)來為此字的WSD模型訓練資料分類，但在實際的分類過程中，發現臺灣客語語料庫的詞類標記方式以及「个」的語法及語意複雜性導致標記人員難以順利執行原定的分類標準。本論文簡化了標記使用的資料分類標準，希望能使「个」詞的多義詞詞意分辨模型的訓練分類更為簡便，使機器學習更有效率。
When Lai (2022) trained the word sense disamguation model for morpheme GE in Taiwan Hakka Corpus, grammatical and functional classification of GE (賴文英, 2012) was adopted to construct its data annotation scheme. However, during the annotation process, the part of speech information of Taiwan Hakka Corpus and the syntactic and semantic complexity of GE let the annotaters find it difficult to abide by the original data annotation scheme. This research simplified the data annotation scheme, hoping to make the WSD data annotation process of GE easier, and therefore the WSD model training more efficient.
參考文獻 朱德熙. (2001). 說“的＂. 中國語文, 12. 收錄於 朱德熙選集 (pp.258 - 289). 長春: 東北師範大學出版社. (原文出版於1961)
朱德熙. (2001). 關於〈說“的＂〉. 中國語文, 1. 收錄於 朱德熙選集 (pp.290 - 307). 長春: 東北師範大學出版社. (原文出版於1966)
朱德熙. (2001). 北京話、廣州話、文水話和福州話里的“的＂字. 方言, 3. 收錄於 朱德熙選集 (pp.308 - 316). 長春: 東北師範大學出版社. (原文出版於1980)
江敏華. (2006). 東勢客家話「同」與「分」的語法特徵及二者之間的關係. [Grammatical Characteristics of tung and bun in Dongshi Hakka and the Relatedness of the Two Markers]. 語言暨語言學, 7(2), 339-364.
賴文英. (2012). 客語的指示代詞. 臺灣: 客家委員會Retrieved from https://www.hakka.gov.tw/Content/Content?NodeID=624&PageID=36503
賴惠玲. (2019). 建置臺灣客語語料庫勞務採購案 第一期程第三次報告-期末成果報告書. 臺灣: 客家委員會
賴惠玲. (2021). 建置臺灣客語語料庫勞務採購案 第二期程第三次報告-期末成果報告書. 臺灣: 客家委員會
Graves, A., Mohamed, A.-r., & Hinton, G. (2013). Speech recognition with deep recurrent neural networks. Paper presented at the 2013 IEEE international conference on acoustics, speech and signal processing.
Huang, H.-c. (2014). Semantic Extensions and the Convergence of the Beneficiary Role: A Case Study of ＂Bun＂ and ＂Lau＂ in Hakka. Concentric： Studies in Linguistics, 40(1), 65-94. doi:10.6241/concentric.ling.40.1.03
Huang, H.-c. (2015). Relating Causative and Passive" Bun" Constructions in Hakka. 清華學報, 45(2), 167-200.
Kim, Y. (2014, oct). Convolutional Neural Networks for Sentence Classification, Paper presented at the Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP).
Lai, H.-L. (2001). On Hakka BUN: A case of polygrammaticalization. LANGUAGE AND LINGUISTICS, 2(2), 137-153.
Lai, H.-L. (2004). The Syntactic Grounding and Conceptualization of Hakka BUN and LAU.
Lai, H.-L. (2015). Profiling Hakka ＂Bun＂ Causative Constructions. [剖析客語「分」致使構式]. 語言暨語言學, 16(3), 369-395. doi:10.1177/1606822x15569164
Lai, H.-L. (2022). Pattern generalizations of Taiwan Hakka polysemy, applications to Taiwan Hakka corpus construction, and their implications to the extant research. (MOST 108-2410-H-004-050-MY3). Taipei, Taiwan: Department of English Literature, National Chengchi University Retrieved from https://www.grb.gov.tw/search/planDetail?id=13786774
Lai, H.-L., Hsu, H.-L., Liu, J.-S., Lin, C.-H., & Chen, Y. (2021a). Supervised Word Sense Disambiguation on Polysemy with Neural Network Models: A Case Study of BUN in Taiwan Hakka. International Journal of Asian Language Processing, 30(03), 2050011.
Lai, H.-L., Hsu, H.-L., Liu, J.-S., Lin, C.-H., & Chen, Y. (2021b). Supervised Word Sense Disambiguation on Taiwan Hakka Polysemy with Neural Network Models: A Case Study of BUN, TUNG and LAU. Paper presented at the Proceedings of the 35th Pacific Asia Conference on Language, Information and Computation.
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781.
Mikolov, T., Yih, W.-t., & Zweig, G. (2013). Linguistic regularities in continuous space word representations. Paper presented at the Proceedings of the 2013 conference of the north american chapter of the association for computational linguistics: Human language technologies.
Tseng, Y.-C. (2012). An optimality theoretic analysis of the distribution of Hakka prepositions DI, DO, BUN, LAU, TUNG, ZIONG. Concentric： Studies in Linguistics, 38(2), 171-209.
描述 碩士
國立政治大學
語言學研究所
108555002
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0108555002
資料類型 thesis
dc.contributor.advisor 賴惠玲zh_TW
dc.contributor.advisor Lai, Hui-Lingen_US
dc.contributor.author (Authors) 陳彥宏zh_TW
dc.contributor.author (Authors) Chen, Yanhongen_US
dc.creator (作者) 陳彥宏zh_TW
dc.creator (作者) Chen, Yanhongen_US
dc.date (日期) 2023en_US
dc.date.accessioned 2-Jun-2023 11:33:41 (UTC+8)-
dc.date.available 2-Jun-2023 11:33:41 (UTC+8)-
dc.date.issued (上傳時間) 2-Jun-2023 11:33:41 (UTC+8)-
dc.identifier (Other Identifiers) G0108555002en_US
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/145037-
dc.description (描述) 碩士zh_TW
dc.description (描述) 國立政治大學zh_TW
dc.description (描述) 語言學研究所zh_TW
dc.description (描述) 108555002zh_TW
dc.description.abstract (摘要) Lai(2022)在訓練臺灣客家語料庫中「个」詞的多義詞詞意分辨模型時，參考了過去的「个」的研究(賴文英, 2012)來為此字的WSD模型訓練資料分類，但在實際的分類過程中，發現臺灣客語語料庫的詞類標記方式以及「个」的語法及語意複雜性導致標記人員難以順利執行原定的分類標準。本論文簡化了標記使用的資料分類標準，希望能使「个」詞的多義詞詞意分辨模型的訓練分類更為簡便，使機器學習更有效率。zh_TW
dc.description.abstract (摘要) When Lai (2022) trained the word sense disamguation model for morpheme GE in Taiwan Hakka Corpus, grammatical and functional classification of GE (賴文英, 2012) was adopted to construct its data annotation scheme. However, during the annotation process, the part of speech information of Taiwan Hakka Corpus and the syntactic and semantic complexity of GE let the annotaters find it difficult to abide by the original data annotation scheme. This research simplified the data annotation scheme, hoping to make the WSD data annotation process of GE easier, and therefore the WSD model training more efficient.en_US
dc.description.tableofcontents 中文摘要 2
英文摘要 2
圖目錄 5
表目錄 5
第一章、研究目的 6
第二章、客語多義詞「分」的自動分類成果 7
2-1 客語多義詞「分」的本體研究 7
2-2 自然語言處理模型：Word2Vec、DNN、Bi-LSTM、textCNN 9
2-3 客語多義詞「分」的自動分類成果 11
2-3-1 訓練資料來源:台灣客語語料庫及其斷詞/詞性標記系統 11
2-3-2 訓練資料的提取與分詞 15
2-4-3 訓練資料分類、人工標記工作及資料清理 16
2-3-4 模型訓練 20
2-3-5 訓練結果 21
第三章、客語多義詞「个」的自動分類議題 26
3-1 客語多義詞「个」的本體研究 26
3-2 客語多義詞「个」的自動分類難題 29
3-3 解決方案 34
3-3-1 訓練資料來源 34
3-3-2 訓練資料的提取與分詞 34
3-3-3 訓練資料的重新分類、人工標記工作及資料清理 35
3-3-4 模型訓練 39
3-4 標記標準更新後的測試結果 39
第四章、結論與意涵 43
4-1 新標記標準實作時遇見的問題 43
4-2 未來研究方向以及限制 45
參考資料 47
中文文獻 47
英文文獻 47		zh_TW
dc.format.extent 1209644 bytes-
dc.format.mimetype application/pdf-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0108555002en_US
dc.subject (關鍵詞) 臺灣客語zh_TW
dc.subject (關鍵詞) 多義詞詞意分辨zh_TW
dc.subject (關鍵詞) 深度學習zh_TW
dc.subject (關鍵詞) 資料標記zh_TW
dc.subject (關鍵詞) Taiwan Hakkaen_US
dc.subject (關鍵詞) Word sense disambiguationen_US
dc.subject (關鍵詞) Deep learningen_US
dc.subject (關鍵詞) Data annotationen_US
dc.title (題名) 多義詞詞性分辨模型的訓練資料準備與前處理: 以臺灣客語「个」為例zh_TW
dc.title (題名) Preparation and Preprocessing of Training Data for Word Sense Disambiguation Model: A Case Study of Taiwan Hakka Polysemy GEen_US
dc.type (資料類型) thesisen_US
dc.relation.reference (參考文獻) 朱德熙. (2001). 說“的＂. 中國語文, 12. 收錄於 朱德熙選集 (pp.258 - 289). 長春: 東北師範大學出版社. (原文出版於1961)
朱德熙. (2001). 關於〈說“的＂〉. 中國語文, 1. 收錄於 朱德熙選集 (pp.290 - 307). 長春: 東北師範大學出版社. (原文出版於1966)
朱德熙. (2001). 北京話、廣州話、文水話和福州話里的“的＂字. 方言, 3. 收錄於 朱德熙選集 (pp.308 - 316). 長春: 東北師範大學出版社. (原文出版於1980)
江敏華. (2006). 東勢客家話「同」與「分」的語法特徵及二者之間的關係. [Grammatical Characteristics of tung and bun in Dongshi Hakka and the Relatedness of the Two Markers]. 語言暨語言學, 7(2), 339-364.
賴文英. (2012). 客語的指示代詞. 臺灣: 客家委員會Retrieved from https://www.hakka.gov.tw/Content/Content?NodeID=624&PageID=36503
賴惠玲. (2019). 建置臺灣客語語料庫勞務採購案 第一期程第三次報告-期末成果報告書. 臺灣: 客家委員會
賴惠玲. (2021). 建置臺灣客語語料庫勞務採購案 第二期程第三次報告-期末成果報告書. 臺灣: 客家委員會
Graves, A., Mohamed, A.-r., & Hinton, G. (2013). Speech recognition with deep recurrent neural networks. Paper presented at the 2013 IEEE international conference on acoustics, speech and signal processing.
Huang, H.-c. (2014). Semantic Extensions and the Convergence of the Beneficiary Role: A Case Study of ＂Bun＂ and ＂Lau＂ in Hakka. Concentric： Studies in Linguistics, 40(1), 65-94. doi:10.6241/concentric.ling.40.1.03
Huang, H.-c. (2015). Relating Causative and Passive" Bun" Constructions in Hakka. 清華學報, 45(2), 167-200.
Kim, Y. (2014, oct). Convolutional Neural Networks for Sentence Classification, Paper presented at the Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP).
Lai, H.-L. (2001). On Hakka BUN: A case of polygrammaticalization. LANGUAGE AND LINGUISTICS, 2(2), 137-153.
Lai, H.-L. (2004). The Syntactic Grounding and Conceptualization of Hakka BUN and LAU.
Lai, H.-L. (2015). Profiling Hakka ＂Bun＂ Causative Constructions. [剖析客語「分」致使構式]. 語言暨語言學, 16(3), 369-395. doi:10.1177/1606822x15569164
Lai, H.-L. (2022). Pattern generalizations of Taiwan Hakka polysemy, applications to Taiwan Hakka corpus construction, and their implications to the extant research. (MOST 108-2410-H-004-050-MY3). Taipei, Taiwan: Department of English Literature, National Chengchi University Retrieved from https://www.grb.gov.tw/search/planDetail?id=13786774
Lai, H.-L., Hsu, H.-L., Liu, J.-S., Lin, C.-H., & Chen, Y. (2021a). Supervised Word Sense Disambiguation on Polysemy with Neural Network Models: A Case Study of BUN in Taiwan Hakka. International Journal of Asian Language Processing, 30(03), 2050011.
Lai, H.-L., Hsu, H.-L., Liu, J.-S., Lin, C.-H., & Chen, Y. (2021b). Supervised Word Sense Disambiguation on Taiwan Hakka Polysemy with Neural Network Models: A Case Study of BUN, TUNG and LAU. Paper presented at the Proceedings of the 35th Pacific Asia Conference on Language, Information and Computation.
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781.
Mikolov, T., Yih, W.-t., & Zweig, G. (2013). Linguistic regularities in continuous space word representations. Paper presented at the Proceedings of the 2013 conference of the north american chapter of the association for computational linguistics: Human language technologies.
Tseng, Y.-C. (2012). An optimality theoretic analysis of the distribution of Hakka prepositions DI, DO, BUN, LAU, TUNG, ZIONG. Concentric： Studies in Linguistics, 38(2), 171-209.		zh_TW