Awards

• Winner: NIPS 2017 Human-Computer Question Answering Competition, Long Beach, CA, USA, 2017 [Paper]
• Second place: WSDM Cup 2017 Triple Scoring Task, Cambridge, UK, 2017 [Paper] [Code]
• Winner: Shared Task in NAACL 2016 Workshop on Human-Computer QA, San Diego, CA, USA, 2016 [Video]
• Winner: Shared Task #1 in ACL 2015 Workshop on Noisy User-generated Text (W-NUT 2015), Beijing, China, 2015 [Paper] [Summary Paper]
• Winner: NEEL Challenge in WWW 2015 Workshop on Making Sense of Microposts (#Microposts 2015), Florence, Italy, 2015 [Paper] [Summary Paper]
• Kaggle Competition Master, 2016
• Keio SFC Student Award: Dean's Award, Keio University Shonan Fujisawa Campus, 2016

Recent Publications

• Representation Learning of Entities and Documents from Knowledge Base Descriptions
  Ikuya Yamada, Hiroyuki Shindo (NAIST), Yoshiyasu Takefuji (Keio)
  International Conference on Computational Linguistics (COLING), 2018 (to appear)
  [Code]
• Studio Ousia's Quiz Bowl Question Answering System
  Ikuya Yamada, Ryuji Tamaki, Hiroyuki Shindo (NAIST), Yoshiyasu Takefuji (Keio)
  First NIPS ’17 Competition, The Springer Series on Challenges in Machine Learning, 2018 (to appear)
• Linkify: Enhancing Text Reading Experience by Detecting and Linking Helpful Entities to Users
  Ikuya Yamada, Tomotaka Ito, Hideaki Takeda (NII), Yoshiyasu Takefuji (Keio)
  IEEE Intelligent Systems, 2018
  [Dataset]
• Learning Distributed Representations of Texts and Entities from Knowledge Base
  Ikuya Yamada, Hiroyuki Shindo (NAIST), Hideaki Takeda (NII), Yoshiyasu Takefuji (Keio)
  Transactions of the Association for Computational Linguistics (TACL), 2017
  [Code]
• Ensemble of Neural Classifiers for Scoring Knowledge Base Triples
  Ikuya Yamada, Motoki Sato (NAIST), Hiroyuki Shindo (NAIST)
  WSDM Cup (Cambridge, UK), 2017 (Ranked 2nd in the competition)
  [Code]
• Named Entity Disambiguation for Noisy Text
  Yotam Eshel (Technion), Noam Cohen (Technion), Kira Radinsky (Technion), Shaul Markovitch (Technion), Ikuya Yamada, Omer Levy (U. Washington)
  The SIGNLL Conference on Computational Natural Language Learning (CoNLL), 2017
• Segment-Level Neural Conditional Random Fields for Named Entity Recognition
  Motoki Sato (NAIST), Hiroyuki Shindo (NAIST), Ikuya Yamada, Yuji Matsumoto (NAIST)
  International Joint Conference on Natural Language Processing (IJCNLP), 2017
• Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation
  Ikuya Yamada, Hiroyuki Shindo (NAIST), Hideaki Takeda (NII), Yoshiyasu Takefuji (Keio)
  The SIGNLL Conference on Computational Natural Language Learning (CoNLL) (Berlin, Germany), 2016
  [Code]
• Enhancing Named Entity Recognition in Twitter Messages Using Entity Linking
  Ikuya Yamada, Hideaki Takeda (NII), Yoshiyasu Takefuji (Keio)
  ACL 2015 Workshop on Noisy User-generated Text (Beijing, China), 2015 (Shared task winner)
• An End-to-End Entity Linking Approach for Tweets
  Ikuya Yamada, Hideaki Takeda (NII), Yoshiyasu Takefuji (Keio)
  WWW 2015 Workshop on Making Sense of Microposts (Florence, Italy), 2015, pp.55-56 (Competition winner)
• Evaluating the Helpfulness of Linked Entities to Readers
  Ikuya Yamada, Tomotaka Ito, Shinsuke Takagi, Shinnosuke Usami, Hideaki Takeda (NII), Yoshiyasu Takefuji (Keio)
  26th ACM Conference on Hypertext and Social Media (Santiago Downtown, Chile), 2014, pp.169-178
  [Dataset]

Open-source Projects

• Wikipedia2Vec: a tool for learning embeddings of words and entities from Wikipedia
• mprpc: a fast Python RPC library
• mojimoji: a fast Python converter for Japanese characters

Working Experience

• 2007- Co-founder, CTO Studio Ousia Inc.
• 2003-2005: Vice President, CTO Fractalist Inc. (previously listed on the NSE Centrex (2007-2010) and acquired by motionBEAT Inc. in 2010)
• 2000-2005: Founder, CEO Newrong Inc. (acquired by Fractalist Inc. in 2005)