Avi Sil  Avi Sil photo         

contact information

Research Staff Member & Chair, NLP Professional Community
IBM Research AI, New York, USA


Professional Associations

Professional Associations:  Association for Computational Linguistics


Work Experience: [ CV ]

  • Team lead, Question Answering, IBM, 2019 - Present
  • NLP Chair, IBM, 2017 - present
  • Research Scientist, IBM, 2014 - present
  • Research Intern, Microsoft Research, Summer 2013
  • Data & Tech Analyst Intern, Morgan Stanley, Summer 2011


  • Session Chair
    • ACL 2019, Question Answering 
    • NAACL 2018, Question Answering

About him: 
Dr. Avi Sil is a Research Scientist in the Multilingual NLP group at IBM Research AI. He is also the Chair of the NLP professional community of IBM. Currently, he is working on industry scale NLP and Deep Learning algorithms. He is
leading a team to work on Question Answering algorithms for the Google Natural Questions challenge and its applications internally. The system name is GAAMA (Go Ahead Ask Me Anything).

His research also includes  Information Extraction: entity recognition and linking and relation extraction. He is a senior program committee member for major Computational Linguistics conferences including being an Area Chair several times. His entity linking system has been the top system several years on TAC KBP evaluations by NIST. He has more than 12 US patents filed all in the area of Artificial Intelligence and it's applications in various spheres.

Avi finished his PhD in Computer Science under the supervision of his thesis advisor Alexander Yates. He also worked on Temporal Information Extraction in the Machine Learning Group at Microsoft Research, Redmond managed by Chris Burges and John Platt. His mentor was Silviu Cucerzan. 

Latest News:

  1. (new) Entity Discovery and Linking for TAC 2019 (along with Heng Ji) is available here
  2. (new) Two papers accepted at EMNLP 2019
  3. Organizing a Question Answering and Semantic Parsing workshop at the IBM Research Week.
  4. Our QA system GAAMA is at Rank 1 (short answers) on the Google Natural Questions challenge. (6/14/19)
  5. Slides from our ACL tutorial are now available here!

Research Interests: 

  • Natural Language Processing
  • Question Answering
  • Information Extraction
  •  Deep Learning