概要 †

知識獲得に関して，自分の研究の相談を行ったり，みんなで論文を読み，議論を行います．

2015年度 †

日時

前期: 毎週火曜日 16:30- 後期: 毎週水曜日10:30-

主な参加者

岡崎，田，周，高瀬，代勤，田中，スミット，小松，島岡，上村，鈴木，コランタン，ダワ，折田

予定・記録 †

• 高瀬
• 3/2(水)
  • 上村 利用物に関する知識のコーパスアノテーション (🔒内部資料)
  • 鈴木 Wikipedia 記事に対する拡張固有表現ラベルの多重付与 🔒内部資料
  • ダワ 🔒内部資料

• 2/17(水)
  • 田: 進捗報告（Learning Semantically-Motivated and Additive Compositional Distributional Representations） 🔒内部資料

• 2/10(水)
  • 小松: 進捗報告 🔒内部資料

• 2/3(水)
  • 岡崎: 論文輪読: 「言語処理における分散表現学習のフロンティア」 🔒内部資料

• 1/28(木)
  • 折田: 論文読み "Event extraction as dependency parsing" paper

• 1/20(水)
  • 代勤 : KA for argument generation 🔒内部資料

• 1/6(水)
  • 周 : 論文紹介 + 進捗報告 🔒内部資料
    • Heng Ji, Joel Nothman, Ben Hachey, Radu Florian. Overview of TAC-KBP2015 Tri-lingual Entity Discovery and Linking. paper

• 12/17(水)
  • スミット: 🔒From CNN to word2vec

• 12/09(水)
  • ダワ: 🔒内部資料
• 12/02(水)
  • 島岡: Wikipediaの全エントリーにWordnet Synset のカテゴリーを割り当てる 🔒内部資料
• 11/25(水)
  • コランタン: Question Answering with Logic Specific to Video Games 🔒内部資料
• 11/11(水)
  • 田: まとまらない話幾つ、本気の研究ネタ一つ 🔒内部資料
• 11/05(木)
  • 上村: 🔒内部資料
• 10/22(木)
  • 小松: 発表練習 🔒内部資料
• 10/13(火)
  • 鈴木: 近況・進捗報告 🔒内部資料

• 10/7(水)
  • 田中：進捗報告＋論文紹介 🔒内部資料
    • Fei Sun, Jiafeng Guo, Yanyan Lan, Jun Xu, and Xueqi Cheng. Learning Word Representations by Jointly Modeling Syntagmatic and Paradigmatic Relations. ACL2015 paper

• 9/16(水)
  • 岡崎: 論文輪読: 単語ベクトル研究の最新動向: 🔒内部資料
    • Omer Levy, Yoav Goldberg, and Ido Dagan. 2015. Improving distributional similarity with lessons learned from word embeddings. TACL, 3:211-225.
    • Karl Stratos, Michael Collins, Daniel Hsu. 2015. Model-based Word Embeddings from Decompositions of Count Matrices. ACL-2015, pages 1282-1291.

• 7/21(火)
  • 島岡：論文輪読 Knowledge Vault: A Web-Scale Approach to Probabilistic Knowledge Fusion paper slide 🔒内部資料
  • 田中：進捗報告 🔒内部資料

• 7/14(火)
  • 高瀬：関係パタンの意味計算 🔒内部資料
  • 代勤：進捗報告 🔒内部資料

• 7/7(火)
  • 田：論文輪読 Deep Unordered Composition Rivals Syntactic Methods for Text Classification paper
  • スミット：論文輪読 Learning from Massive Noisy Labeled Data for Image Classification paper 🔒内部資料

• 6/30(火)
  • 小松: 進捗報告 🔒内部資料

• 6/23(火)
  • 関根さん: 🔒内部資料

• 6/16(火)
  • 島岡: 進捗報告 🔒内部資料

• 6/9(火)
  • 田中: 論文輪読；Omer Levy, Yoav Goldberg，Linguistic Regularities in Sparse and Explicit Word Representations，CoNLL2014，paper，🔒内部資料
  • 代勤: 論文紹介: Niels Kasch and Tim Oates. Mining Script-Like Structures from Web. Proceedings of the NAACL HLT 2010 First International Workshop on Formalisms and Methodology for Learning by Reading. paper,🔒Slides

• 6/2(火)
  • スミット: 進捗報告 🔒内部資料

• 5/26(火): 休会（NL研）

• 5/20(水): 発表練習
  • 小松: 🔒内部資料
  • 横井: 🔒内部資料
  • 清野: 🔒内部資料
  • 高瀬: 🔒内部資料

• 5/19(火)
  • 休会

• 5/12(火)
  • 小松: 進捗報告 🔒内部資料

• 4/28(火)
  • チュートリアル: 山口さん 🔒内部資料

• 4/21(火)
  • 岡崎: 論文輪読: Wojciech Zaremba, Ilya Sutskever. (2014-) Learning to Execute. arXiv.org (paper) (slides) (🔒内部資料) (参考資料1) (参考資料2)
  • 高瀬: 論文輪読: Manaal Faruqui, Jese Dodge, Sujay K. Jauhar, Chris Dyer, Eduard Hovy, Noah A. Smith., Retrofitting Word Vectors toSemantic Lexicons., NAACL2015., paper 🔒内部資料

• 4/14(火): 休会（MICS）

• 4/7(火)
  • 岡崎（＋全員）：イントロダクションと研究紹介 🔒内部資料
  • 田：キックオフ 🔒内部資料

参考文献 †

チュートリアル・招待講演 †

• Fabian M. Suchanek, Martin Theobald, Gerhard Weikum, Hady W. Lauw and Ralf Schenkel. Semantic Knowledge Bases from Web Sources. IJCAI 2011.
• Marius Pasca. Web-Based Open-Domain Information Extraction. WWW 2011.
• Hans Uszkoreit. Learning Relation Extraction Grammars with Minimal Human Intervention: Strategy, Results, Insights and Plans. CICling 2011.
• Oren Etzioni. Machine Reading at Web Scale. WSDM 2008.
• Tom Mitchell. Learning, Information Extraction and the Web. PKDD 2007.

全般 †

• Satoshi Sekine. Semantic Knowledge Discovery.
• Oren Etzioni, Michele Banko, Stephen Soderland and Daniel S. Weld. Open Information Extraction from the Web. Communications of the ACM, 2008.
• Andrew Carlson, Justin Betteridge, Richard C. Wang, Estevam R. Hruschka, Jr, Tom M. Mitchell. Coupled semi-supervised learning for information extraction, WSDM 2010.

固有表現抽出 †

• Patrick Pantel and Deepak Ravichandran. Automatically Labeling Semantic Classes. HLT-NAACL '04.
• Patrick Pantel and Marco Pennacchiotti. Espresso: Leveraging Generic Patterns for Automatically Harvesting Semantic Relations. Coling-ACL '06.
• Oren Etzioni, Michael Cafarella, Doug Downey, Ana-Maria Popescu, Tal Shaked, Stephen Soderland, Daniel S. Weld, and Alexander Yates. Unsupervised Named-Entity Extraction from the Web: An Experimental Study. Artificial Intelligence, 165(1), 91-134, 2005.
• Jun’ichi Kazama and Kentaro Torisawa. Exploiting Wikipedia as External Knowledge for Named Entity Recognition. EMNLP '07.
• Jun Suzuki and Hideki Isozaki. Semi-Supervised Sequential Labeling and Segmentation Using Giga-Word Scale Unlabeled Data. ACL '08.
• Lev Ratinov and Dan Roth. Design Challenges and Misconceptions in Named Entity Recognition. CoNLL '09.
• Jenny Rose Finkel and Christopher D. Manning. Nested Named Entity Recognition. ACL '09.
• Dan Wu, Wee Sun Lee, Nan Ye and Hai Leong Chieu. Domain adaptive bootstrapping for named entity recognition. EMNLP' 09.
• Ruihong Huang and Ellen Riloff. Inducing Domain-Specific Semantic Class Taggers from (Almost) Nothing. ACL '10.
• Jenny Rose Finkel and Christopher D. Manning. Hierarchical Joint Learning: Improving Joint Parsing and Named Entity Recognition with Non-Jointly Labeled Data. ACL '10.
• Stefan Rüd, Massimiliano Ciaramita, Jens Müller and Hinrich Schütze. Piggyback: Using Search Engines for Robust Cross-Domain Named Entity Recognition. ACL '11.

エンティティ知識獲得 †

Marius Pasca, Dekang Lin, Jeffrey Bigham, Andrei Lifchits, Alpa Jain. Organizing and Searching the World Wide Web of Facts - Step One: the One-Million Fact Extraction Challenge. AAAI '06.

関係抽出 †

• Makoto Miwa and Rune Sætre and Yusuke Miyao and Jun’ichi Tsujii. A Rich Feature Vector for Protein-Protein Interaction Extraction from Multiple Corpora, EMNLP '09.
• Yee Seng Chan and Dan Roth. Exploiting Syntactico-Semantic Structures for Relation Extraction. ACL '11.
• Anthony Fader, Stephen Soderland, and Oren Etzioni. Identifying Relations for Open Information Extraction. EMNLP '11.

含意・因果関係 †

• Jonathan Berant, Ido Dagan, Jacob Goldberger. Learning Entailment Relations by Global Graph Structure Optimization, Computational Linguistics, Vol. 38, No. 1, Pages 73-111, March 2012.
• Oren Etzioni, Anthony Fader, Janara Christensen, Stephen Soderland, and Mausam. Open Information Extraction: The Second Generation, AAAI 2011.
• Rajat Raina, Andrew Y. Ng, and Christopher D. Manning. Robust textual inference via learning and abductive reasoning, AAAI '05.
• Nathanael Chambers and Daniel Jurafsky. Unsupervised Learning of Narrative Event Chains, ACL '08.
• Stefan Schoenmackers and Oren Etzioni and Daniel S. Weld and Jesse Davis. Learning first-order Horn clauses from web text. EMNLP '10.
• Mark Sammons, V. G. Vinod Vydiswaran and Dan Roth. "Ask not what Textual Entailment can do for You...". ACL '10.
• Jonathan Berant, Ido Dagan, and Jacob Goldberger. Global learning of focused entailment graphs. ACL' 10.
• Raphael Hoffmann, Congle Zhang, Xiao Ling, Luke Zettlemoyer, and Daniel S. Weld. Knowledge-Based Weak Supervision for Information Extraction of Overlapping Relations. ACL' 11.
• Jonathan Berant, Ido Dagan and Jacob Goldberger. Global Learning of Typed Entailment Rules. ACL' 11.
• Andrew Carlson, Justin Betteridge, Bryan Kisiel, Burr Settles, Estevam R. Hruschka Jr., and Tom M. Mitchell. 2010. Toward an architecture for neverending language learning. AAAI 2010.
• Peter LoBue and Alexander Yates. Types of Common-Sense Knowledge Needed for Recognizing Textual Entailment. ACL 2011.
• Quang Xuan Do, Yee Seng Chan, and Dan Roth. Minimally Supervised Event Causality Identification, EMNLP 2011.
• Chikara Hashimoto, Kentaro Torisawa, Kow Kuroda, Masaki Murata, and Jun'ichi Kazama. Large-Scale Verb Entailment Acquisition from the Web, EMNLP 2009