Special Interest Group on Discourse (SIG Discourse) discusses research progress of our member (5-10 min. each) and interesting findings of past/state-of-the-art researches (30 min.). The schedule is listed below.

Date †

• 1st Semester: Wed 13:00-14:30

Members †

乾, 井之上, Paul, 横井, 高橋, 清野, 赤間, 白井, 栗林, 大内, 佐藤(志), 大竹, Ana

Related Keywords †

人工知能/Artificial Intelligence，物語理解/Story Understanding，プラン/Plan，修辞構造/Rhetorical Structure，照応/Anaphora，省略/Ellipsis，ゼロ照応/Zero Anaphora

Policy †

多読会と個別議論を交互にやる。

• 多読会
  • 目的
    • 最新論文100本を多読し、分野の方向感掴み、脳内へのポインタ作りを行う
    • 多読力をつける (短い時間で研究の概形を把握する, 短い時間で疑問/感想を持つ)
  • 実施要領
    • 3本 x {7, 8, 9,10}人 (コアメン) = 最低20本程度の論文を多読する
    • 1本3分でやる
    • 目標: 100本
    • 詳しくは🔒こちら
• 個別議論
  • 各回3名が担当
    • 論文紹介・研究進捗報告など、自由に選んでよい
    • だいたい1ヶ月に1度当番が回ってくる
    • 忙しければ 自由に 延期
  • 精読
    • 発表前に読む論文を #random で紹介
    • 30分でQA含めキッチリ切る。
  • 進捗
    • 30-40分でQA含め。普段の総合研究会より深めの議論をするため。
    • 進捗は議論が長くなる傾向にあるので、進捗が少なくとも一個入るならば2セットで勉強会を組む
• 聞きかた
  • 各回1度は質問・コメントをする

Schedule †

Future †

• Thu 3/7 10:30-
  • 精読 or 進捗:
  • 精読 or 進捗:
  • 精読 or 進捗:

• Thu 2/28 10:30-
  • 精読: 赤間 (2)
  • 精読 or 進捗: 大内 (3)
  • 精読 or 進捗: 高橋 (3)

• Thu 2/14 10:30-

• 精読: 清野 (2)
• 精読: 白井 (3) What Is One Grain of Sand in the Desert ? Analyzing Individual Neurons in Deep NLP Models, AAAI2019.
  • 🔒内部資料 ， paper

• Thu 2/7 10:30-
  • 進捗: Ana (1)
    • Progress report and task idea 🔒内部資料
  • 進捗: 井之上 (2)
    • 🔒内部資料
  • 進捗: Shiki (2)
    • 🔒内部資料

Done †

• Thu 1/31 10:30-
  • 進捗: 大竹 (2)
    • 顕現的要素の出現順序に基づく物語の類似性尺度 🔒内部資料
  • 精読 or 進捗: 栗林 (2)
  • 精読 or 進捗: 内藤 (2)

• Thu 12/13 10:30-
  • 精読: 横井 (2)
    • McInnes+'18, UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction, arXiv
    • paper, 🔒内部資料
  • 精読: 高橋 (2)
    • Yuhao Zhang, Peng Qi, Christopher D. Manning. Graph Convolution over Pruned Dependency Trees Improves Relation Extraction. EMNLP 2018
    • paper, 🔒内部資料

• Thu 12/6 10:30-
  • 精読: 佐藤 (志)
    • Yang Zhao, Yining Wang, Jiajun Zhang, Chengqing Zong. Phrase Table as Recommendation Memory for Neural Machine Translation. IJCAI 2018
    • paper 🔒内部資料
  • 進捗: 大内 (2)
  • 精読: 赤間 (1)
    • Lajanugen Logeswaran, Honglak Lee, Samy Bengio. Content preserving text generation with attribute controls. NIPS2018
    • paper, 内部資料

• Thu 11/29 10:30-
  • 精読1: 井之上 (1)
    • Haitian Sun, Bhuwan Dhingra, Manzil Zaheer, Kathryn Mazaitis, Ruslan Salakhutdinov, William W. Cohen. Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text. EMNLP 2018.
    • paper 🔒内部資料
  • 精読2: 大竹
    • Towards Automatically Extracting Story Graphs from Natural Language Stories (Josep Valls-Vargas, et al., AAAI2017 Workshop on What's Next for AI in Games?)
    • paper 🔒内部資料
  • 進捗: 白井 (1) 🔒内部資料

• Thu 11/22 10:30-
  • 多読会5 (92本目〜108本目 🎉) 🔒資料

• Thu 11/15 10:30
  • 多読会4 (67本目〜) 🔒資料

• Thu 10/25 10:30-
  • 精読1: 井之上
    • Haitian Sun, Bhuwan Dhingra, Manzil Zaheer, Kathryn Mazaitis, Ruslan Salakhutdinov, William W. Cohen. Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text. EMNLP 2018.
    • paper 内部資料
  • 精読2: 栗林
    • Jiaqi Mu, Pramod Viswanath. All-but-the-Top: Simple and Effective Postprocessing for Word Representations. ICLR 2018.
    • Mikhail Khodak, Nikunj Saunshi, Yingyu Liang, Tengyu Ma, Brandon Stewart, Sanjeev Arora. A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors. ACL2018.
    • All-but-the-Top A La Carte 🔒内部資料
  • 進捗: 内藤 🔒進捗報告

• Thu 10/18 10:30-
  • 精読1: 横井
    • David Alvarez-Melis, Tommi S. Jaakkola. Gromov-Wasserstein Alignment of Word Embedding Spaces. EMNLP 2018.
    • arXiv, 🔒内部資料
  • 精読2: 高橋
    • Eunsol Choi, He He, Mohit Iyyer, Mark Yatskar, Wen-tau Yih, Yejin Choi, Percy Liang, Luke Zettlemoyer. QuAC : Question Answering in Context. EMNLP 2018.
    • paper, 🔒annotated paper
  • 進捗: 佐藤S 🔒進捗報告

• Thu 10/11 10:30-
  • 多読会3 (42本目〜) 🔒資料

• Fri 10/5 14:15-
  • 多読会2 (23本目〜) 🔒資料

• Wed 9/26 13:00-
  • 続・なつやすみの... (B4)
  • 多読会1 (1本目〜) 🔒資料

• Wed 9/19 13:00-
  • なつやすみの...

• Wed 7/25 13:00-
  • B team
  • 井之上 🔒内部資料
    • Hannah Rashkin, Maarten Sap, Emily Allaway, Noah A. Smith, and Yejin Choi. Event2Mind: Commonsense Inference on Events, Intents, and Reactions. ACL2018. paper project home

• Wed 7/11 13:00-
  • A team
  • 内藤

• Wed 7/4 13:00-
  • B team
  • 赤間 ごめんなさい

• Wed 6/27 13:00-
  • A team
  • 栗林 🔒スライド 🔒Universal sentence encoder 🔒Learning General Purposeなんとか

• Wed 6/20 13:00-
  • B team
  • 白井 🔒esa

• Wed 6/13 13:00-
  • A team
  • 大内: 🔒進捗報告
• Wed 6/6 13:00-
  • 清野 (1)
• Wed 5/30 13:00-
  • B team
  • 横井: 🔒最近の進捗と今後やりたいこと

• Wed 5/16 13:00-
  • A team
  • Paul: 🔒進捗報告

• Wed 5/9 13:00-
  • B team
  • 井之上: 🔒進捗報告

• Wed 4/25 13:00-
  • A team

• Wed 4/11, 13:00-
  • 研究紹介
    • 井之上: 🔒キックオフ 🔒推論！
    • Paul: 🔒 内部資料
    • 横井: 🔒やっていた研究とやっている研究
    • 高橋: 🔒研究紹介
    • 清野: 🔒就活の資料を切り貼りしたもの
    • 赤間: 🔒「あなたの研究内容について教えてください」
    • 白井:🔒内部資料
    • 栗林:🔒内部資料

Assignment †

• v: presented
• (v): assigned

前期 †

Team †

Past †

• Spring 2017-Winter 2018
• Spring 2016-Winter 2017
• Spring 2015-Winter 2016
• Spring 2014-Winter 2015
• Spring 2013-Winter 2014
• Spring 2012-Winter 2013
• Spring 2011-Winter 2012
• Spring 2010-Winter 2011

Links †

Artificial Intelligence †

• Levesque, Hector J. "On our best behaviour." The 23rd International Joint Conference on Artificial Intelligence (IJCAI). August. 2013. pdf
• Rahman, Altaf, and Vincent Ng. "Resolving complex cases of definite pronouns: the winograd schema challenge." Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. Association for Computational Linguistics, 2012. pdf dataset dataset 2
• Roemmele, Melissa, Cosmin Adrian Bejan, and Andrew S. Gordon. "Choice of Plausible Alternatives: An Evaluation of Commonsense Causal Reasoning." AAAI Spring Symposium: Logical Formalizations of Commonsense Reasoning. 2011. pdf dataset
• Levesque, Hector J., Ernest Davis, and Leora Morgenstern. "The Winograd schema challenge." AAAI Spring Symposium: Logical Formalizations of Commonsense Reasoning. 2011. pdf
• Jerry R. Hobbs, Mark Stickel, Douglas Appelt, and Paul Martin. Interpretation as Abduction, Artificial Intelligence, 1993. pdf

Logical Inference †

• Mohammad Shahed Sorower, Thomas G. Dietterich, Janardhan Rao Doppa Walker Orr, Prasad Tadepalli, and Xiaoli Fern. Inverting Grice’s Maxims to Learn Rules from Natural Language Extractions. NIPS 2011. pdf
• Ekaterina Ovchinnikova, Niloofar Montazeri, Theodore Alexandrov, Jerry R. Hobbs, Michael C. McCord and Rutu Mulkar-Mehta. Abductive Reasoning with a Large Knowledge Base for Discourse Processing. IWCS 2011. pdf
• James Blythe, Jerry R. Hobbs, Pedro Domingos, Rohit J. Kate and Raymond J. Mooney. Implementing Weighted Abduction in Markov Logic. IWCS2011. pdf
• Dan Garrette, Katrin Erk, Raymond Mooney. Integrating Logical Representations with Probabilistic Information using Markov Logic. IWCS2011. pdf
• Sindhu V. Raghavan, Raymond J. Mooney. Bayesian Abductive Logic Programs. AAAI 2010. pdf
• RohitJ. Kate RaymondJ. Mooney. Probabilistic Abduction using Markov Logic Networks. IJCAI 2009 on PAIR 2009. pdf
• Jerry R. Hobbs, Mark Stickel, Douglas Appelt, and Paul Martin. Interpretation as Abduction, Artificial Intelligence, 1993. pdf
• J. Bos (2009): Applying automated deduction to natural language understanding. Journal of Applied Logic 7(1): 100–112. pdf
• A Unified Approach to Abductive Inference (ARO 2008 MURI Project@University of Washington)

Discourse Theory †

• Rhetorical Structure Theory
• Discourse Representation Theory
• J. Bos, M. Nissim (2008): Combining Discourse Representation Theory with FrameNet. In: R. Rossini Favretti (ed): Frames, Corpora, and Knowledge Representation, pp 169–183, Bononia University Press. pdf
• Dan Cristea, Nancy Ide and Laurent Romary. Veins Theory: A Model of Global Discourse Cohesion and Coherence. ACL 1998. pdf
• Barbara J. Grosz, Aravind K. Joshi and Scott Weinstein. Centering: A Framework for Modeling the Local Coherence of Discourse. Computational Linguistics, 1995. pdf
• Barbara J. Grosz and Candace L. Sidner. ATTENTION, INTENTIONS, AND THE STRUCTURE OF DISCOURSE. Computational Linguistics, 1986. pdf

• Bonnie Webber. Accounting for Discourse Relations: Constituency and Dependency. Intelligent Linguistic Architectures, 2006. pdf
• Florian Wolf, Edward Gibson. Representing Discourse Coherence: A Corpus-Based Study. Computational Linguistics, 2005.
• Bonnie Webber, Matthew Stone, Aravind Joshi and Alistair Knott. Anaphora and Discourse Structure. Computational Linguistics, 2003. pdf
• Daniel Marcu. A Formal and Computational Synthesis of Grosz and Sidner's and Mann and Thompson's theories. 1999. pdf
• Erhard Hinrichs. Discourse Annotation of Corpora. pdf
• Johanna D. Moore and Martha E. Pollack. A Problem for RST: The Need for Multi-Level Discourse Analysis. Computational Linguistics, 1992. pdf

Discourse Parsing †

• Alexis Palmer, Afra Alishahi and Caroline Sporleder. Robust Semantic Analysis for Unseen Data in FrameNet. RANLP2011. pdf
• Michaela Regneri, Alexander Koller, Josef Ruppenhofer and Manfred Pinkal. Learning Script Participants from Unlabeled Data. RANLP2011. pdf
• Manfred Klenner and Don Tuggener. An Incremental Entity-Mention Model for Coreference Resolution with Restrictive Antecedent Accessibility. RANLP2011. pdf
• Ziheng Lin, Hwee Tou Ng and Min-Yen Kan. Automatically Evaluating Text Coherence Using Discourse Relation. ACL 2011. pdf
• Ziheng Lin, Hwee Tou Ng, and Min-Yen Kan. A PDTB-Styled End-to-End Discourse Parser. 2010. pdf
• Annie Louis, Rashmi Prasad, Aravind Joshi and Ani Nenkova. Using Entity Features to Classify Implicit Discourse Relations. SIGDIAL 2010. pdf
• Aria Haghighi and Dan Klein. Coreference Resolution in a Modular, Entity-Centered Model. NAACL-HLT 2010. pdf
• Emily Pitler, Annie Louis and Ani Nenkova. Automatic sense prediction for implicit discourse relations in text. ACL-IJCNLP 2009. pdf
• Rajen Subba and Barbara Di Eugenio. An effective Discourse Parser that uses Rich Linguistic Information. NAACL-HLT 2009. pdf
• Ravikiran Vadlapudi, Poornima Malepati and Suman Yelati. Hierarchical Discourse Parsing Based on Similarity Metrics. RANLP 2009. pdf
• Manfred Klenner, Étienne Ailloud. Optimization in Coreference Resolution is not Needed: A Nearly-Optimal Algorithm with Intensional Constraints. EACL 2009. pdf
• Jason Baldridge and Alex Lascarides. Probabilistic Head-Driven Parsing for Discourse Structure. CoNLL 2005. pdf
• Daniel Marcu and Abdessamad Echihabi. An Unsupervised Approach to Recognizing Discourse Relations. ACL 2002. pdf

Plan Recognition †

• Parag Singla and Raymond J. Mooney. Abductive Markov Logic for Plan Recognition. AAAI2011. pp 1069-1075. pdf
• Nate Blaylock and James Allen. Hierarchical Instantiated Goal Recognition. MOO2006. pdf
• Nate Blaylock and James Allen. Fast Hierarchical Goal Schema Recognition. AAAI2006. pdf
• Douglas E. Appelt and Martha E. Pollack. Weighted Abduction for Plan Ascription. Technical Note 491, SRI International, 1992. pdf
• Sandra Carberry. Techniques for Plan Recognition. User Modeling and User-Adapted Interaction, 11(1-2), pp. 31-48, 2001. pdf

Corpus †

• Penn Discourse Treebank
• RST Discourse Treebank
• Discourse Graphbank: paper LDC
• SDRT annotations of dialogues: DISCOR project

Knowledge Acquisition †

• Doo Soon Kim and Bruce Poter. Integrating declarative knowledge : Issues, Algorithms and Future Work. AAAI2008. pdf
• Jonathan Berant, Tel Aviv and Jacob Goldberger. Global Learning of Typed Entailment Rules. ACL2011. (to appear) pdf
• Stefan Schoenmackers, Jesse Davis, Oren Etzioni and Daniel Weld. Learning First-Order Horn Clauses from Web Text. EMNLP2010. pdf
• Nathanael Chambers and Dan Jurafsky. Unsupervised Learning of Narrative Schemas and their Participants. ACL2010. pdf

Lectures †

• University of Southern California: Introduction to NLP, Empirical Methods in Natural Language Processing
• MIT: Computational Models of Discourse
• Tohoku University: http://www.is.tohoku.ac.jp/_eng/introduction/laboratories/sis/iis_cs.html
• Story Understanding Resources
• David Poole and Alan Mackworth. Artificial Intelligence: Foundations of Computational Agents

Tools †

• WOFMC
• Stanford CoreNLP
• Mini-TACITUS
• PRISM
• enju
• C&C tools

Misc. †

• University of Texas at Austin Machine Learning Group: Publications
• Linguistic Problems and Complexities