EMNLP/2008

EMNLP 2008 読み会

日時

• 第1回:2008年11月14日(金) 19:00-
• 第2回はなし

場所

A707

目的

• EMNLP 2008 の論文をサーベイすることで最新の動向を知る。
• 来年のシンガポールに向けて英気を養う。

形式

• 1人の持ち時間20分程度で興味のある論文を1本紹介。
• BYOB (Bring Your Own Bottle) でアルコール飲みながらの聴講可。
• カレー部と共催

参加希望者(発表者はプログラムのところに先着順でタイトルを書いてください)

• 11月14日
  • ryu-i, mamoru-k, katsumasa-y, yotaro-w, matsu, hideharu-o, masakazu-i, naoya-i, ai-a, tomohiro-s
  • 中川哲治(NICT)

プログラム

11月14日(金)

EMNLP 論文集

Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing にタイトルと PDF がある

楽な [論文の 探し方] あるいは [楽な 論文の] 探し方

• WhatToSee にアクセス
• 自分の使っている bibTeX のファイルを送信して EMNLP 2008 のところにチェックを入れて Submit すると、恐らくリンク解析的手法を使って自分に関連した論文のランキングが出てくる
  • 10月30日現在まだ使えません

既に他の勉強会で紹介された論文

• CJE
  • Razvan Bunescu, "Learning with Probabilistic Features for Improved Pipeline Models"
• 対話
  • Higuchi, Shinsuke and Rzepka, Rafal and Araki, Kenji, "A Casual Conversation System Using Modality and Word Associations Retrieved from the Web"

コメント

• 岡崎直観さん
  • Sujith Ravi; Kevin Knight. Attacking Decipherment Problems Optimally with Low-Order N-gram Models.
  • Gabriel Murray; Giuseppe Carenini. Summarizing Spoken and Written Conversations.
  • Vivi Nastase. Topic-Driven Multi-Document Summarization with Encyclopedic Knowledge and Spreading Activation.
  • Xiaojun Wan. An Exploration of Document Impact on Graph-Based Multi-Document Summarization.
  • Arul Menezes; Chris Quirk. Syntactic Models for Structural Word Insertion and Deletion during Translation.
  • Roser Morante; Anthony Liekens; Walter Daelemans. Learning the Scope of Negation in Biomedical Texts.
  • Mark Dredze; Koby Crammer. Online Methods for Multi-Domain Learning and Adaptation.
  • Hal Daumé III. Cross-Task Knowledge-Constrained Self Training.
  • Razvan Bunescu. Learning with Probabilistic Features for Improved Pipeline Models.
  • Imed Zitouni; Radu Florian. Mention Detection Crossing the Language Barrier.
  • Partha Pratim Talukdar; Joseph Reisinger; Marius Pasca; Deepak Ravichandran; Rahul Bhagat; Fernando Pereira. Weakly-Supervised Acquisition of Labeled Class Instances using Graph Random Walks.
  • Phil Blunsom; Miles Osborne. Probabilistic Inference for Machine Translation.
  • Chris Callison-Burch. Syntactic Constraints on Paraphrases Extracted from Parallel Corpora.
  • André Filipe Torres Martins; Dipanjan Das; Noah A. Smith; Eric P. Xing. Stacking Dependency Parsers.
  • David Smith; Jason Eisner. Dependency Parsing by Belief Propagation.
  • Slav Petrov; Aria Haghighi; Dan Klein. Coarse-to-Fine Syntactic Machine Translation using Language Projections.
  • Ron Bekkerman; Koby Crammer. One-Class Clustering in the Text Domain.
  • Omar Zaidan; Jason Eisner. Modeling Annotators: A Generative Approach to Learning from Annotator Rationales.
  • Yunyao Li; Rajasekar Krishnamurthy; Sriram Raghavan; Shivakumar Vaithyanathan; H. V. Jagadish. Regular Expression Learning for Information Extraction.
  • Jeremy Jancsary; Johannes Matiasek; Harald Trost. Revealing the Structure of Medical Dictations with Conditional Random Fields.
• mamoru-k
  • EMNLP 2008 最終日
    • Katrin Erk and Sebastian Padó. A Structured Vector Space Model for Word Meaning in Context.
    • Einat Minkov and William Cohen. Learning Graph Walk Based Similarity Measures for Parsed Text.
    • Hinrich Schuetze and Michael Walsh. A graph-theoretic model of lexical syntactic acquisition.
    • Cory Barr, Rosie Jones and Moira Regelson. The Linguistic Structure of English Web-Search Queries.
    • Zhifei Li and David Yarowsky. Mining and Modeling Relations between Formal and Informal Chinese Phrases from Web Corpora.
  • EMNLP 2008 2日目
    • Partha Pratim Talukdar, Joseph Reisinger, Marius Pasca, Deepak Ravichandran, Rhul Bhagat and Fernando Pereira. Weakly-Supervised Acquisition of Labeled Class Instances using Graph Random Walks.
    • Razvan Bunescu. Learning with Probabilistic Features for Improved Pipeline Models.
    • Hal Daume III. Cross-Task Knowledge-Constrained Self Training.
    • Dredze and Koby Crammer. Online Methods for Multi-Domain Learning and Adaptation Mark.
  • EMNLP 2008 初日
    • Shane Bergsma, Dekang Lin and Randy Goebel. Discriminative Learning of Selectional Preference from Unlabeled Text.
    • Ron Bekkerman and Koby Crammer. One-Class Clustering in the Text Domain.
    • Ben Sandbank. Refining Generative Language Models using Discriminative Learning.
    • Andre' Filipe Torres Matins, Dipanjan Das, Noah A. Smith and Eric P. Xing. Stacking Dependency Parsers.
    • Haitao Mi and Liang Huang. Forest-based Translation Rule Extraction.
    • Rion Snow, Brendan O'Connor, Daniel Jurafsky and Andrew Ng. Cheap and Fast -- But is it Good? Evaluating Non-Expert Annotations for Natural Language Tasks.