|Class#||Date||Lead||Materials/Deadlines||Topics and Readings|
|1||1/08 (Tue)||Jan Wiebe||Course webpage||Welcome and Administration|
|2||1/10 (Thu)||Jan Wiebe||
Subjectivity and Sentiment Analysis: From Words to Discourse
... to Pragmatics
Cem Akkaya, Janyce Wiebe, Alexander Conrad, and Rada Mihalcea (2011). Improving the Impact of Subjectivity Word Sense Disambiguation on Contextual Opinion Analysis. CoNLL 2011
Swapna Somasundaran and Janyce Wiebe (2009). Recognizing Stances in Online Debates. ACL-IJCNLP 2009.
|3||1/15 (Tue)||Jan Wiebe||
The MPQA corpus, subjectivity lexicon, and word-sense annotations can be downloaded from my website once CSSD goes live with our new page.
Sections 1.1-1.2, 2.0, 3.1, 7.1 of Theresa Wilson's Dissertation
Sections 1 & 2 of Janyce Wiebe, Theresa Wilson, and Claire Cardie (2005). Annotating expressions of opinions and emotions in language. Language Resources and Evaluation, volume 39, issue 2-3, pp. 165-210
|4||1/17 (Thu)||Lingjia|| Commentaries start today;
enter into NB by 2pm the day before
Bing Liu makes severcal datasets available at his sentiment page.
Product Review Mining
Minqing Hu and Bing Liu Mining and Summarizing Customer Reviews KDD-2004.
Kim, Soo-Min and Hovy, Eduard Automatic Identification of Pro and Con Reasons in Online Reviews. COLING-ACL-2006.
Product Review Mining, continued
Oscar Tackstrom and Ryan McDonald (2011). Discovering Fine-Grained Sentiment with Latent Variable Structured Prediction Models ECIR-2011.
Ana-Maria Popescu and Oren Etzioni (2005). Extracting Product Features and Opinions from Reviews EMNLP-2005. Also, joint extraction.
Barbosa, Luciano and Kumar, Ravi and Pang, Bo and Tomkins, Andrew (2009). For a few dollars less: Identifying review pages sans human labels. NAACL-2009.
|6||1/24 (Thu)||Jan Wiebe||Introductory slides||
Ron Artstein and Massimo Poesio. Inter-coder agreement for computational linguistics (survey article). Computational Linguistics 34(4): 555-596, 2008
The Toprak et al. data may be downloaded from *this page*
Aspects and Review Objects
Mukherjee, Arjun and Liu, Bing Aspect Extraction through Semi-Supervised Modeling. ACL-2012.
Toprak, Cigdem and Jakob, Niklas and Gurevych, Iryna (2010) Sentence and Expression Level Annotation of Opinions in User-Generated Discourse. ACL-2010. Aspect-based annotations.
Dalvi, Nilesh and Kumar, Ravi and Pang, Bo and Tomkins, Andrew Matching Reviews to Objects using a Language Model EMNLP-2009.
Yu, Jianxing and Zha, Zheng-Jun and Wang, Meng and Chua, Tat-Seng (2011). Aspect Ranking: Identifying Important Product Aspects from Online Consumer Reviews. ACL-2011.
Wei, Wei and Gulla, Jon Atle (2010). Sentiment Learning on Product Reviews via Sentiment Ontology Tree. ACL-2010.
Brody, Samuel and Elhadad, Noemie (2010). An Unsupervised Aspect-Sentiment Model for Online Reviews NAACL-2010.
Identifying Holders and Targets/Topics
Stoyanov, Veselin and Cardie, Claire (2008). Topic Identification for Fine-Grained Opinion Analysis COLING-2008.
Choi, Yejin and Cardie, Claire and Riloff, Ellen and Patwardhan, Siddharth (2005). Identifying Sources of Opinions with Conditional Random Fields and Extraction Patterns. EMNLP-2005.
Jakob, Niklas and Gurevych, Iryna (2010). Extracting Opinion Targets in a Single and Cross-Domain Setting with Conditional Random Fields EMNLP-2011.
|10||2/07 (Thu)||Huy||Project meetings completed||
Ivan Titov and Ryan McDonald (2008). A Joint Model of Text and Aspect Ratings for Sentiment Summarization ACL-2008.
Zhao, Xin and Jiang, Jing and Yan, Hongfei and Li, Xiaoming (2010). Jointly Modeling Aspects and Opinions with a MaxEnt-LDA Hybrid EMNLP-2010.
Ivan Titov and Ryan McDonald (2008). Modeling online reviews with multi-grain topic models. WWW-2008.
|11||2/12(Tue)||Yoonjung||The data from the Somasundaran et al. paper is available.||
Joint Extraction/Recognition, continued
Choi, Yejin and Breck, Eric and Cardie, Claire (2006). Joint Extraction of Entities and Relations for Opinion Recognition EMNLP-2006.
Somasundaran, Swapna and Namata, Galileo and Wiebe, Janyce and Getoor, Lise (2009). Supervised and Unsupervised Methods in Employing Discourse Relations for Improving Opinion Polarity Classification EMNLP 2009.
Du, Weifu and Tan, Songbo (2009). An Iterative Reinforcement Approach for Fine-Grained Opinion Mining ACL-2009.
|12||2/14 (Thu)||Jesse||The data for Murray and Carenini is available *here*||
Carenini, Giuseppe and Ng, Raymond T. and Zhou, Xiaodong (2008). Summarizing Emails with Conversational Cohesion and Subjectivity ACL-2008.
Murray, Gabriel and Carenini, Giuseppe (2009). Predicting Subjectivity in Multimodal Conversations. EMNLP-2009.
Minqing Hu and Bing Liu (2006). Opinion Extraction and Summarization on the Web. AAAI-2006.
Project proposals due
TAC 2008 Opinion Question Answering Track. For the Opinion Question answering track, we would need a user agreement for the Blog6 data.
Oh, Jong-Hoon and Torisawa, Kentaro and Hashimoto, Chikara and Kawada, Takuya and De Saeger, Stijn and Kazama, Jun'ichi and Wang, Yiou (2012). Why Question Answering using Sentiment Analysis and Word Classes EMNLP-2012. This is also related to connotation.
Paul, Michael and Zhai, ChengXiang and Girju, Roxana (2010). Summarizing Contrastive Viewpoints in Opinionated Text. EMNLP-2010.
Lerman, Kevin and McDonald, Ryan (2009). Sentiment Summarization: Evaluating and Learning User Preferences. EACL-2009.
Subjectivity annotation, continued from Day 3, 1/15.
Bollegala, Danushka and Weir, David and Carroll, John (2011). Using Multiple Sources to Construct a Sentiment Sensitive Thesaurus for Cross-Domain Sentiment Classification. ACL 2011.
Blitzer, John and Dredze, Mark and Pereira, Fernando, Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification ACL-2007.
He, Yulan and Lin, Chenghua and Alani, Harith (2011). Automatically Extracting Polarity-Bearing Topics for Cross-Domain Sentiment Classification ACL-2011.
Recognizing Stances, Arguments, and Viewpoints
Swapna Somasundaran and Janyce Wiebe (2009). Recognizing Stances in Online Debates. ACL-IJCNLP 2009.
Walker, M. and Anand, P and Abbott, R. and Tree, J.E.F. and Martell,C. and King, J. (2011). That's your evidence:? Classifying Stance in Online Political and Social Debate. Decision Support Sciences. 1-30. Elsevier. 2011 (based on their WASSA 2011 paper that won the best paper award).
Y. Lu and H. Wang and C. Zhai and D. Roth (2012). Unsupervised Discovery of Opposing Opinion Networks From Forum Discussions. CIKM-2012.
Recognizing Stances, Arguments, Viewpoints, continued.
Park, Souneil and Lee, Kyung Soon and Song, Junehwa (2011). Contrasting Opposing Views of News Articles on Contentious Issues. ACL-2011.
Abu-Jbara, Amjad and Dasigi, Pradeep and Diab, Mona and Radev, Dragomir (2011). Subgroup Detection in Ideological Discussions. ACL-2011.
Lin, Wei-Hao and Hauptmann, Alexander (2006). Are These Documents Written from Different Perspectives? A Test of Different Perspectives Based on Statistical Distribution Divergence. ACL-2006.
Argument data: Death Penalty (Baumgartner, Boef, Boydstun); ConvinceMe.net (Conrad).
|19||3/19 (Tue)||Lingjia||See the bullet of "Data related to sentiment analysis" on Lillian Lee's data site||
Bo Pang and Lillian Lee (2004). A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum Cuts ACL-04.
Feng, Song and Bose, Ritwik and Choi, Yejin (2011). Learning General Connotation of Words using Graph-based Algorithms EMNLP-2011. This is also related to connotation.
Li, Binyang and Zhou, Lanjun and Feng, Shi and Wong, Kam-Fai (2010). A Unified Graph Model for Sentence-Based Opinion Retrieval. ACL-2010.
|20||3/21 (Thu)||Huichao||Project progress reports due||
Phrase-Level Contextual Polarity
Theresa Wilson, Janyce Wiebe, and Paul Hoffmann (2005). Recognizing Contextual Polarity in Phrase-Level Sentiment Analysis, EMNLP-2009.
Agarwal, Apoorv and Biadsy, Fadi and Mckeown, Kathleen (2009). Contextual Phrase-Level Polarity Analysis Using Lexical Affect Scoring and Syntactic N-Grams. EACL 2009.
Socher, Richard, Huval, Brody, Manning, Christopher D. and Ng, Andrew Y. (2012). Semantic Compositionality through Recursive Matrix-Vector Spaces. EMNLP 2012.
Phrase-Level Contextual Polarity, continued
Yejin Choi and Claire Cardie (2008). Learning with Compositional Semantics as Structural Inference for Subsentential Sentiment Analysis. EMNLP-2008.
Karo Moilanen and Stephen Pulman (2007). Sentiment Composition. RANLP 2007.
Yessenalina, Ainur and Cardie, Claire (2011). Compositional Matrix-Space Models for Sentiment Analysis. EMNLP-2011.
Conceptual Dependency Theory and Scripts
Chapters 1-3 of Roger Schank and Robert Abelson (1977). Scripts, Plans, Goals and Understanding. Lawrence Erlbaum.
|Data created by Chambers and Jurafsky is available *here*||
Learning Narrative and Script Schemas
Chambers, Nathanael and Jurafsky, Dan (2008). Unsupervised Learning of Narrative Event Chains ACL-2008.
Regneri, Michaela and Koller, Alexander and Pinkal, Manfred (2010) Learning Script Knowledge with Web Experiments ACL-2010.
Chambers, Nathanael and Jurafsky, Dan (2009). Unsupervised Learning of Narrative Schemas and their Participants ACL-2009.
Chambers, Nathanael and Jurafsky, Dan (2009). A Database of Narrative Schemas LREC-2010
Wendy Lehnert. Plot Units and Narrative Summarization. Cognitive Science 4 (1981).
Goyal, Amit and Riloff, Ellen and Daume III, Hal (2012). A Computational Model for Plot Units. Computational Intelligence, 2012.
Resurrecting "Old AI"
I've requested the data annotated in Ganter and Strube.
The CoNLL-2010 shared task was on detecting hedges and their scope. The data is available *here*.
Ganter, Viola and Strube, Michael (2009). Finding Hedges by Chasing Weasels: Hedge Detection Using Wikipedia Tags and Shallow Linguistic Features. ACL-IJCNLP-2009 short paper.
Medlock, Ben and Briscoe, Ted (2007). Weakly Supervised Learning for Hedge Classification in Scientific Literature. ACL-2007.
Richard Farkas (2010). The CoNLL-2010 Shared Task (the overview paper at the beginning). CoNLL-2010.
|27||4/16 (Tue)||Jan||Project report draft due||
de Marneffe, Marie-Catherine; Christopher D. Manning; and Christopher Potts. 2012. Did it happen? The pragmatic complexity of veridicality assessment. Computational Linguistics 38(2): 301-333
rabhakaran, Vinodkumar and Rambow, Owen and Diab, Mona (2010). Automatic Committed Belief Tagging. COLING-2010.
|28||4/18 (Thu)||Class is cancelled.|
Final project reports due.
|Project presentations: Jesse, Lingjia and Yoonjung, Fan and Wencan. 25 minutes each, including questions.|
|30||4/25 (Thu)||Project presentations. Alex and Phuong; Huy and Huichao. 25 minutes each, including questions.|