請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/84640完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 魏志平(Chih-Ping Wei) | |
| dc.contributor.author | How Jiang | en |
| dc.contributor.author | 姜皜 | zh_TW |
| dc.date.accessioned | 2023-03-19T22:18:39Z | - |
| dc.date.copyright | 2022-09-19 | |
| dc.date.issued | 2022 | |
| dc.date.submitted | 2022-09-15 | |
| dc.identifier.citation | Araque O, Zhu G, Iglesias CA (2019) A semantic similarity-based perspective of affect lexicons for sentiment analysis. Knowl.-Based Syst. 165:346–359. Bao L, Lambert P, Badia T (2019) Attention and Lexicon Regularized LSTM for Aspect-based Sentiment Analysis. Proc. 57th Annu. Meet. Assoc. Comput. Linguist. Stud. Res. Workshop. (Association for Computational Linguistics, Florence, Italy), 253–259. Brody S, Elhadad N (2010) An Unsupervised Aspect-Sentiment Model for Online Reviews. Hum. Lang. Technol. 2010 Annu. Conf. North Am. Chapter Assoc. Comput. Linguist. (Association for Computational Linguistics, Los Angeles, California), 804–812. Byrkjeland M, Gørvell de Lichtenberg F, Gambäck B (2018) Ternary Twitter Sentiment Classification with Distant Supervision and Sentiment-Specific Word Embeddings. Proc. 9th Workshop Comput. Approaches Subj. Sentim. Soc. Media Anal. (Association for Computational Linguistics, Brussels, Belgium), 97–106. Cho K, van Merrienboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, Bengio Y (2014) Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. (September 2) http://arxiv.org/abs/1406.1078. Denecke K, Deng Y (2015) Sentiment analysis in medical settings: New opportunities and challenges. Artif. Intell. Med. 64(1):17–27. Deng S, Sinha AP, Zhao H (2017) Adapting sentiment lexicons to domain-specific social media texts. Decis. Support Syst. 94:65–76. Devlin J, Chang MW, Lee K, Toutanova K (2019) BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. ArXiv181004805 Cs. Fu P, Lin Z, Yuan F, Wang W, Meng D (2018) Learning Sentiment-Specific Word Embedding via Global Sentiment Representation. Proc. AAAI Conf. Artif. Intell. 32(1). Gui L, Hu J, He Y, Xu R, Lu Q, Du J (2017) A Question Answering Approach to Emotion Cause Extraction. (September 23) http://arxiv.org/abs/1708.05482. Hamilton WL, Clark K, Leskovec J, Jurafsky D (2016) Inducing Domain-Specific Sentiment Lexicons from Unlabeled Corpora. Proc. Conf. Empir. Methods Nat. Lang. Process. Conf. Empir. Methods Nat. Lang. Process. 2016:595–605. He R, Lee WS, Ng HT, Dahlmeier D (2018) Effective Attention Modeling for Aspect-Level Sentiment Classification. Proc. 27th Int. Conf. Comput. Linguist. (Association for Computational Linguistics, Santa Fe, New Mexico, USA), 1121–1131. Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput. 9(8):1735–1780. Hofmann T (2001) Unsupervised Learning by Probabilistic Latent Semantic Analysis. Mach. Learn. 42(1):177–196. Hu M, Liu B Mining and Summarizing Customer Reviews. :10. Jakob N, Gurevych I (2010) Extracting Opinion Targets in a Single and Cross-Domain Setting with Conditional Random Fields. Proc. 2010 Conf. Empir. Methods Nat. Lang. Process. (Association for Computational Linguistics, Cambridge, MA), 1035–1045. Jiang L, Yu M, Zhou M, Liu X, Zhao T (2011) Target-dependent Twitter Sentiment Classification. Proc. 49th Annu. Meet. Assoc. Comput. Linguist. Hum. Lang. Technol. (Association for Computational Linguistics, Portland, Oregon, USA), 151–160. Jin W, Ho HH A Novel Lexicalized HMM-based Learning Framework for Web Opinion Mining. Khan FH, Qamar U, Bashir S (2017) A semi-supervised approach to sentiment analysis using revised sentiment strength based on SentiWordNet. Knowl. Inf. Syst. 51(3):851–872. Khan L, Amjad A, Afaq KM, Chang HT (2022) Deep Sentiment Analysis Using CNN-LSTM Architecture of English and Roman Urdu Text Shared in Social Media. Appl. Sci. 12(5):2694. Kiritchenko S, Zhu X, Cherry C, Mohammad S (2014) NRC-Canada-2014: Detecting Aspects and Sentiment in Customer Reviews. Proc. 8th Int. Workshop Semantic Eval. SemEval 2014. (Association for Computational Linguistics, Dublin, Ireland), 437–442. Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc. IEEE 86(11):2278–2324. Li X, Bing L, Li P, Lam W (2019) A Unified Model for Opinion Target Extraction and Target Sentiment Prediction. Proc. AAAI Conf. Artif. Intell. 33(01):6714–6721. Li X, Lam W (2017) Deep Multi-Task Learning for Aspect Term Extraction with Memory Interaction. Proc. 2017 Conf. Empir. Methods Nat. Lang. Process. (Association for Computational Linguistics, Copenhagen, Denmark), 2886–2892. Liu B (2012) Sentiment Analysis and Opinion Mining. Synth. Lect. Hum. Lang. Technol. 5(1):1–167. Liu P, Joty S, Meng H (2015) Fine-grained Opinion Mining with Recurrent Neural Networks and Word Embeddings. Proc. 2015 Conf. Empir. Methods Nat. Lang. Process. (Association for Computational Linguistics, Lisbon, Portugal), 1433–1443. Liu Q, Gao Z, Liu B, Zhang Y (2013) A Logic Programming Approach to Aspect Extraction in Opinion Mining. 2013 IEEEWICACM Int. Jt. Conf. Web Intell. WI Intell. Agent Technol. IAT. 276–283. Mao Y, Shen Y, Yu C, Cai L (2021) A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysis. Proc. AAAI Conf. Artif. Intell. 35(15):13543–13551. Mechulam N, Salvia D, Rosá A, Etcheverry M (2019) Building Dynamic Lexicons for Sentiment Analysis. Intel. Artif. 22(64):1–13. Meena A, Prabhakar TV (2007) Sentence Level Sentiment Analysis in the Presence of Conjuncts Using Linguistic Analysis. Amati G, Carpineto C, Romano G, eds. Adv. Inf. Retr. Lecture Notes in Computer Science. (Springer, Berlin, Heidelberg), 573–580. Pennington J, Socher R, Manning C (2014) GloVe: Global Vectors for Word Representation. Proc. 2014 Conf. Empir. Methods Nat. Lang. Process. EMNLP. (Association for Computational Linguistics, Doha, Qatar), 1532–1543. Rhanoui M, Mikram M, Yousfi S, Barzali S (2019) A CNN-BiLSTM Model for Document-Level Sentiment Analysis. Mach. Learn. Knowl. Extr. 1(3):832–847. Singh VK, Piryani R, Uddin A, Waila P (2013) Sentiment analysis of movie reviews: A new feature-based heuristic for aspect-level sentiment classification. 2013 Int. Mutli-Conf. Autom. Comput. Commun. Control Compress. Sens. IMac4s. 712–717. Strapparava C, Valitutti A (2004) WordNet-Affect: an Affective Extension of WordNet. Vol 4 4. Tang D, Qin B, Feng X, Liu T (2016) Effective LSTMs for Target-Dependent Sentiment Classification. Proc. COLING 2016 26th Int. Conf. Comput. Linguist. Tech. Pap. (The COLING 2016 Organizing Committee, Osaka, Japan), 3298–3307. Tang D, Wei F, Qin B, Zhou M, Liu T (2014) Building Large-Scale Twitter-Specific Sentiment Lexicon : A Representation Learning Approach. Proc. COLING 2014 25th Int. Conf. Comput. Linguist. Tech. Pap. (Dublin City University and Association for Computational Linguistics, Dublin, Ireland), 172–182. Teng Z, Vo DT, Zhang Y (2016) Context-Sensitive Lexicon Features for Neural Sentiment Analysis. Proc. 2016 Conf. Empir. Methods Nat. Lang. Process. (Association for Computational Linguistics, Austin, Texas), 1629–1638. Wang J, Zhang Y, Yu LC, Zhang X (2022) Contextual sentiment embeddings via bi-directional GRU language model. Knowl.-Based Syst. 235:107663. Wang W, Pan SJ, Dahlmeier D, Xiao X (2017) Coupled Multi-Layer Attentions for Co-Extraction of Aspect and Opinion Terms. Proc. AAAI Conf. Artif. Intell. 31(1). Wang Y, Huang M, Zhu X, Zhao L (2016) Attention-based LSTM for Aspect-level Sentiment Classification. Proc. 2016 Conf. Empir. Methods Nat. Lang. Process. (Association for Computational Linguistics, Austin, Texas), 606–615. Wilson T, Wiebe J, Hoffmann P (2005) Recognizing Contextual Polarity in Phrase-Level Sentiment Analysis. Proc. Hum. Lang. Technol. Conf. Conf. Empir. Methods Nat. Lang. Process. (Association for Computational Linguistics, Vancouver, British Columbia, Canada), 347–354. Xia R, Ding Z (2019) Emotion-Cause Pair Extraction: A New Task to Emotion Analysis in Texts. (June 4) http://arxiv.org/abs/1906.01267. Xia Y, Cambria E, Hussain A, Zhao H (2015) Word Polarity Disambiguation Using Bayesian Model and Opinion-Level Features. Cogn. Comput. 7(3):369–380. Zhang L, Liu B, Lim SH, O’Brien-Strain E (2010) Extracting and Ranking Product Features in Opinion Documents. Coling 2010 Posters. (Coling 2010 Organizing Committee, Beijing, China), 1462–1470. Zhang Z, Lan M (2015) Learning sentiment-inherent word embedding for word-level and sentence-level sentiment analysis. 2015 Int. Conf. Asian Lang. Process. IALP. 94–97. Zhu J, Wang H, Tsou BK, Zhu M (2009) Multi-aspect opinion polling from textual reviews. Proc. 18th ACM Conf. Inf. Knowl. Manag. CIKM ’09. (Association for Computing Machinery, New York, NY, USA), 1799–1802. Zhu X, Zhang M, Hong Y, He R eds. (2020) Natural Language Processing and Chinese Computing: 9th CCF International Conference, NLPCC 2020, Zhengzhou, China, October 14–18, 2020, Proceedings, Part II (Springer International Publishing, Cham). Zou Y, Gui T, Zhang Q, Huang X (2018) A Lexicon-Based Supervised Attention Model for Neural Sentiment Analysis. Proc. 27th Int. Conf. Comput. Linguist. (Association for Computational Linguistics, Santa Fe, New Mexico, USA), 868–877. Wu Y (2019), A neural multi-task learning for aspect extraction and sentiment classification. Unpublished master thesis, Department of Information Management, National Taiwan University. Wang C (2020), Neural Multi-task Learning Combined with Sentiment Lexicon for Aspect-based Sentiment Analysis. Unpublished master thesis, Department of Information Management, National Taiwan University. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/84640 | - |
| dc.description.abstract | 情感分析是多年來自然語言處理問題中很受歡迎的一個大類別。例如在屬性層級的情感分析的問題中，研究者經常使用外部的情感辭典來改進其模型的表現。而各種聚焦在情感辭典萃取方法的文獻也逐漸增加，近年來以深度學習模型自動化辭典萃取過程的方法尤其受到歡迎。 然而情感辭典會遇到的問題是許多情感字詞並不見得永遠代表正面或是負面的涵意。根據它們所形容的對象不同，有些情感字詞可能會代表完全相反的情感極性。這使我們認為建立出一個能帶有「意見字詞」(Opinion words)以及「意見-目標字詞之間的相依性資訊」的情感辭典將會對於其他應用辭典的情感分析任務有更大的幫助。 雖然許多文獻著重於萃取用於屬性層級的情感分析之情感辭典，但是只有少數的文獻針對「意見-目標字詞之間的相依性資訊」進行分析與萃取。因此，我們在這篇論文中將提出一種基於多任務深度學習網路訓練之模型架構作為情感辭典萃取方法，不僅針對文字的情感極性做萃取，更能同時聚焦在意見字詞以及其修飾的目標字詞之間的相依性上。實驗證明我們提出的模型架構，確實能有效地捕捉到部分意見-目標字詞相依性的資訊，並獲得更佳的萃取結果。 | zh_TW |
| dc.description.abstract | Sentiment analysis is a popular category of natural language processing tasks over years. In many categories of tasks, such as aspect-based sentiment analysis task, prior studies often use external sentiment lexicons to improve the effectiveness of their models. More and more studies focusing on developing sentiment lexicon extraction methods have been proposed. In recent years, the corpus-based lexicon extraction approach using the deep learning models is particularly popular. The problem with existing sentiment lexicons, however, is that many opinion words do not always have the same positive or negative polarity. Depending on targets, some opinion words may represent completely opposite sentiment polarities. This leads us to consider that building a sentiment lexicon with information of the dependencies between opinion words and their corresponding target words extracted from a given corpus may be helpful for other sentiment analysis tasks using external sentiment lexicons. Although many prior studies focus on extracting lexicons for aspect-based sentiment analysis, only few of them analyze and identify the dependencies between opinions and their target words. Therefore, in this research, we will propose a deep-learning-based sentiment lexicon extraction method using the multi-task learning, which not only focuses on the dependencies between opinions and their target words, but also extracts the sentiment polarity of input documents (product reviews) at the same time. Experiments show that our proposed method can effectively capture the dependencies of opinion words and their target words. | en |
| dc.description.provenance | Made available in DSpace on 2023-03-19T22:18:39Z (GMT). No. of bitstreams: 1 U0001-1409202216463600.pdf: 1806823 bytes, checksum: 6322d491f93c8aa9c30bf63e2d7cb3f9 (MD5) Previous issue date: 2022 | en |
| dc.description.tableofcontents | 致謝 i 摘要 ii Abstract iii Table of Contents iv List of Tables vii List of Figures ix Chapter 1 Introduction 1 1.1 Background 1 1.2 Research Motivation 4 Chapter 2 Literature Review 6 2.1 Sentiment Lexicon Extraction 6 2.2 Aspect-based Sentiment Analysis 10 2.3 Summary 14 Chapter 3 Methodology 15 3.1 Problem Definition 15 3.2 Phase 1: Opinion Extraction 17 3.2.1 Overview 17 3.2.2 Task 1: Opinion dependency sequence labeling task 18 3.2.3 Task 2: Opinion polarity sequence labeling task 21 3.2.4 Task 3: Polarity-dependency sequence labeling 22 3.3 Phase 2: Target Extraction 23 3.3.1 Overview 23 3.2.2 Task 4: Target sequence labeling 24 3.2.3 Joint training 25 Chapter 4 Empirical Evaluation 26 4.1 Datasets 26 4.2 Evaluation Metrics 28 4.3 Experiment 1: Our Proposed Model 29 4.3.1 Experiment settings 29 4.3.2 Experiment results 30 4.4 Experiment 2: 2-stacked Bi-GRU Model 32 4.4.1 Experiment settings 32 4.4.2 Experiment results 33 4.5 Experiment 3: Adding Sentence Level Sentiment Polarity 35 4.5.1 Experiment settings 35 4.5.2 Experiment results 35 4.6 Experiment 4: Ablation Experiment of Removing Dependency Task 37 4.6.1 Experiment settings 37 4.6.2 Experiment results 37 4.7 Experiment 5: Ablation Experiment of Not Concatenating Features 38 4.7.1 Experiment settings 39 4.7.2 Experiment results 39 4.8 The Extracted Sentiment Lexicon 41 Chapter 5 Conclusions 43 References 44 | |
| dc.language.iso | en | |
| dc.subject | 情感辭典萃取 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 多任務學習 | zh_TW |
| dc.subject | 屬性層級的情感分析 | zh_TW |
| dc.subject | 意見-目標字詞相依 | zh_TW |
| dc.subject | Multi-task learning | en |
| dc.subject | Sentiment lexicon extraction | en |
| dc.subject | Opinion-target word dependency | en |
| dc.subject | Aspect-based sentiment analysis | en |
| dc.subject | Deep learning | en |
| dc.title | 基於多任務深度學習網路訓練之情感辭典萃取方法 | zh_TW |
| dc.title | A multi-task deep neural network method for sentiment lexicon extraction | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 110-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 吳家齊(Chia-Chi Wu),楊錦生(Chin-Sheng Yang) | |
| dc.subject.keyword | 深度學習,多任務學習,屬性層級的情感分析,意見-目標字詞相依,情感辭典萃取, | zh_TW |
| dc.subject.keyword | Deep learning,Aspect-based sentiment analysis,Sentiment lexicon extraction,Opinion-target word dependency,Multi-task learning, | en |
| dc.relation.page | 47 | |
| dc.identifier.doi | 10.6342/NTU202203407 | |
| dc.rights.note | 同意授權(限校園內公開) | |
| dc.date.accepted | 2022-09-16 | |
| dc.contributor.author-college | 管理學院 | zh_TW |
| dc.contributor.author-dept | 資訊管理學研究所 | zh_TW |
| dc.date.embargo-lift | 2022-09-19 | - |
| 顯示於系所單位： | 資訊管理學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-1409202216463600.pdf 授權僅限NTU校內IP使用（校園外請利用VPN校外連線服務） | 1.76 MB | 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。