Improvement of Syntactic Dependency Analysis by Syntax Pattern Acquisition and Coordinate Structure Analysis

• Project/Area Number: 26240035
• Research Category: Grant-in-Aid for Scientific Research (A)
• Allocation Type: Single-year Grants
• Section: 一般
• Research Field: Intelligent informatics
• Research Institution: Nara Institute of Science and Technology
• Principal Investigator: Matsumoto Yuji 奈良先端科学技術大学院大学, 情報科学研究科, 教授 (10211575)
• Co-Investigator(Kenkyū-buntansha): 新保 仁 奈良先端科学技術大学院大学, 情報科学研究科, 准教授 (90311589) ; Duh Kevin (DUH Kevin) 奈良先端科学技術大学院大学, 情報科学研究科, 助教 (80637322) ; 進藤 裕之 奈良先端科学技術大学院大学, 情報科学研究科, 助教 (20734784) ; 能地 宏 奈良先端科学技術大学院大学, 情報科学研究科, 助教 (00782541)
• Project Period (FY): 2014-04-01 – 2017-03-31
• Project Status: Completed (Fiscal Year 2016)
• Budget Amount: ¥34,060,000 (Direct Cost: ¥26,200,000、Indirect Cost: ¥7,860,000); Fiscal Year 2016: ¥10,660,000 (Direct Cost: ¥8,200,000、Indirect Cost: ¥2,460,000); Fiscal Year 2015: ¥11,050,000 (Direct Cost: ¥8,500,000、Indirect Cost: ¥2,550,000); Fiscal Year 2014: ¥12,350,000 (Direct Cost: ¥9,500,000、Indirect Cost: ¥2,850,000)
• Keywords: 自然言語処理 / 統語解析 / 並列構造 / 複文構造 / 依存構造解析 / 機械学習 / アノテーション / コーパス / 多言語処理 / 並列構造解析 / 構文パターン / 構文解析

Outline of Final Research Achievements

Aiming at an improvement of syntactic dependency analysis of English sentences, we compiled an English multi-word expression (MWE) lexicon and an MWE-annotated corpus. We also developed an algorithm for coordination structure analysis on top of dependency structure analysis.
For English MWEs, we collected English functional multi-word expressions and performed MWE annotation on Penn Treebank. We also implemented an MWE-aware English dependency parsing algorithm. We collected English complex sentence patterns and made annotation on made annotation on complex sentence examples.
For coordinate structure analysis, we proposed a joint algorithm of dependency and coordinate structure analysis and implemented a prototype system.

Research Products

• [Journal Article] Transition-Based Dependency Parsing Exploiting Supertags (2016)
  • Author(s): Hiroki Ouchi, Kevin Duh, Hiroyuki Shindo, and Yuji Matsumoto
  • Journal Title: IEEE/ACM Transactions on Audio, Speech, and Language Processing Volume: 24 Issue: 11 Pages: 2059-2068
  • DOI: 10.1109/taslp.2016.2598310
  • Peer Reviewed / Int'l Joint Research / Acknowledgement Compliant
• [Presentation] 依存構造情報を用いた柔軟な複単語表現の同定 (2017)
  • Author(s): 森元彩華, 吉本暁文, 加藤明彦, 進藤裕之, 松本裕治
  • Organizer: 言語処理学会第23回年次大会
  • Place of Presentation: 茨城県つくば市
  • Year and Date: 2017-03-16
• [Presentation] 固有表現と複合機能語を考慮したMWEベースの依存構造コーパス構築と解析 (2017)
  • Author(s): 加藤明彦, 進藤裕之, 松本裕治
  • Organizer: 言語処理学会第23回年次大会
  • Place of Presentation: 茨城県つくば市
  • Year and Date: 2017-03-14
• [Presentation] 日本語Universal Dependenciesへの複合辞情報付加の試み (2017)
  • Author(s): 久保大輝, 田中貴秋, 進藤裕之, 松本裕治, 永田昌明
  • Organizer: 言語処理学会第23回年次大会
  • Place of Presentation: 茨城県つくば市
  • Year and Date: 2017-03-14
• [Presentation] 複単語表現を考慮した英語の依存構造解析モデリング (2016)
  • Author(s): 加藤明彦・進藤裕之・松本裕治
  • Organizer: 情報処理学会 第229回自然言語処理研究会
  • Place of Presentation: 東京都武蔵野市
  • Year and Date: 2016-12-22
• [Presentation] Identification of Flexible Multiword Expressions with the Help of Dependency Structure Annotation (2016)
  • Author(s): Ayaka Morimoto, Akifumi Yoshimoto, Akihiko Kato, Hiroyuki Shindo, and Yuji Matsumoto
  • Organizer: the Workshop on Grammar and Lexicon: interactions and interfaces
  • Place of Presentation: Osaka, Japan
  • Year and Date: 2016-12-11
  • Int'l Joint Research
• [Presentation] A Generalized Framework for Hierarchical Word Sequence Language Model (2016)
  • Author(s): Xiaoyi Wu, Kevin Duh, and Yuji Matsumoto
  • Organizer: The 30th Pacific Asia Conference on Language, Information and Computation
  • Place of Presentation: Seoul, Korea
  • Year and Date: 2016-10-29
  • Int'l Joint Research
• [Presentation] Parsing Complex Linguistic Constructions (2016)
  • Author(s): Yuji Matsumoto
  • Organizer: The Eighth International Conference on Knowledge and Systems Engineering
  • Place of Presentation: Hanoi, Vietnam
  • Year and Date: 2016-10-07
  • Int'l Joint Research / Invited
• [Presentation] Construction of an English Dependency Corpus incorporating Compound Function Words (2016)
  • Author(s): Akihiko Kato, Hiroyuki Shindo, and Yuji Matsumoto
  • Organizer: the Tenth International Conference on Language Resources and Evaluation
  • Place of Presentation: Portoroz, Slovenia
  • Year and Date: 2016-05-26
  • Int'l Joint Research
• [Presentation] An Improved Hierarchical Word Sequence Language Model Using Word Association (2015)
  • Author(s): Xiaoyi Wu, Yuji Matsumoto, Kevin Duh, Hiroyuki Shindo
  • Organizer: Statistical Language and Speech Processing
  • Place of Presentation: Budapest, Hungary
  • Year and Date: 2015-11-24
  • Int'l Joint Research
• [Presentation] An Efficient Annotation for Phrasal Verbs using Dependency Information (2015)
  • Author(s): Masayuki Komai, Hiroyuki Shindo, Yuji Matsumoto
  • Organizer: The 29th Pacific Asia Conference on Language, Information and Computation
  • Place of Presentation: Shanghai, China
  • Year and Date: 2015-10-30
  • Int'l Joint Research
• [Presentation] An Improved Hierarchical Word Sequence Language Model Using Directional Information (2015)
  • Author(s): Xiaoyi Wu, Yuji Matsumoto
  • Organizer: The 29th Pacific Asia Conference on Language, Information and Computation
  • Place of Presentation: Shanghai, China
  • Year and Date: 2015-10-30
  • Int'l Joint Research
• [Presentation] 複合機能語を考慮した英語の依存構造コーパスの構築 (2015)
  • Author(s): 加藤明彦，進藤裕之，松本裕治
  • Organizer: 情報処理学会 第223回自然言語処理研究会 Vol.2015-NL-223
  • Place of Presentation: 広島経済大学（広島県広島市）
  • Year and Date: 2015-09-27
• [Presentation] Coordination-aware dependency parsing (2015)
  • Author(s): Akifumi Yoshimoto, Kazuo Hara, Masashi Shimbo, Yuji Matsumoto
  • Organizer: The 14th International Conference on Parsing Technologies
  • Place of Presentation: Bilbao, the Basque Country
  • Year and Date: 2015-07-22
  • Int'l Joint Research
• [Presentation] CKY Parsing with Independence Constraints (2015)
  • Author(s): Joseph Irwin, Yuji Matsumoto
  • Organizer: The 14th International Conference on Parsing Technologies
  • Place of Presentation: Bilbao, the Basque Country
  • Year and Date: 2015-07-22
  • Int'l Joint Research
• [Presentation] 並列構造解析に向けた依存構造解析アルゴリズムの拡張 (2015)
  • Author(s): 吉本暁文, 新保仁, 原一夫, 松本裕治
  • Organizer: 情報処理学会 第221回自然言語処理研究会 第106回音声言語情報処理研究会 共催研究会 Vol.2015-NL-221
  • Place of Presentation: 東北大学（宮城県仙台市）
  • Year and Date: 2015-05-25
• [Presentation] 英語の句動詞表現の同定とコーパス構築 (2015)
  • Author(s): 駒井雅之, 進藤裕之, 松本裕治
  • Organizer: 言語処理学会第21回年次大会
  • Place of Presentation: 京都大学（京都府京都市）
  • Year and Date: 2015-03-17 – 2015-03-19
• [Presentation] 係り受け情報を利用した日本語形態素解析 (2015)
  • Author(s): 俵雄貴, 東藍, 松本裕治
  • Organizer: 情報処理学会 第220回自然言語処理研究会
  • Place of Presentation: 九州大学医学部百年講堂(福岡県福岡市）
  • Year and Date: 2015-01-19 – 2015-01-20
• [Presentation] A Hierarchical Word Sequence Language Model (2014)
  • Author(s): Xiaoyi Wu and Yuji Matsumoto
  • Organizer: 28th Pacific Asia Conference on Language, Information and Computation
  • Place of Presentation: Phuket (Thailand)
  • Year and Date: 2014-12-12 – 2014-12-14
• [Presentation] Supertagの曖昧性を考慮した依存構造解析 (2014)
  • Author(s): 大内啓樹, Kevin Duh, 進藤裕之, 松本裕治
  • Organizer: 情報処理学会研究報告 第218回自然言語処理研究会
  • Place of Presentation: 首都大学東京（東京都八王子市）
  • Year and Date: 2014-09-01 – 2014-09-02