Avi Sil  Avi Sil photo         

contact information

Principal Research Scientist & Research Manager - Multilingual Question Answering
IBM Research AI, New York, USA
  

links

Professional Associations

Professional Associations:  Association for Computational Linguistics

profile


Work Experience: [ CV ]

  • Research Manager, IBM, Jun 2021 - Present
  • Principal Research Scientist, IBM, May 2021 - Present
  • Team lead, Question Answering + Information Retrieval, IBM, Jan 2019 - Jun 2021
  • NLP Chair, IBM, 2017 - present
  • Research Scientist, IBM, May 2014 - May 2021
  • Research Intern, Microsoft Research, Summer 2013
  • Data & Tech Analyst Intern, Morgan Stanley, Summer 2011

Chair:

  • Demo Chair:
    • NAACL 2021
  • Diversity and Inclusion Chair:
    • Chair of the Academic Inclusion team at ACL 2021
  • Organizer:
  • Shared Task Coordinator
    • 2020: Fine grained entity extraction at Text Analysis Conference (TAC), (co lead along with Heng Ji)
    • 2019: Entity Discovery and Linking task at Text Analysis Conference (TAC), (co lead along with Heng Ji)
  • Area Chair (Tracks: Question Answering & Information Extraction)
    • 2020: ACL, EMNLP
    • 2019: CoNLL, ACL, NAACL
    • 2018: NAACL, COLING
  • Session Chair
    • ACL 2019, Question Answering 
    • NAACL 2018, Question Answering

About him: 
Dr. Avi Sil is a Principal Research Scientist and a Research Manager in the Multilingual NLP group at IBM Research AI. He leads the Question Answering and Information Retrieval team (comprising of research scientists and engineers) and is one of the creators of the GAAMA system. His team works on cutting edge research on industry scale NLP and Deep Learning algorithms.
He is also the Chair of the NLP professional community of IBM.

His research also includes  Information Extraction: entity recognition and linking and relation extraction. He co-leads the TAC KBP track for Entity Discovery and Linking (EDL) along with Dr. Heng Ji. 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) Two papers at ACL 2021 (on QA and IE) and 1 at SIGIR 2021 (Neural IR for Domain Adaptation)
  2.  Two papers at NAACL 2021. 1. QA over tables and 2. Event time extraction
  3. Two papers at AAAI 2021. Will be also teaching a tutorial at EMNLP21 on Multilingual Multi-domain QA along with Sebastian Ruder.
  4. Invited talk at UCLA NLP Group (Nov 20). Host: Kai-wei Chang
  5. Invited talk at Vaibhav Summit (Oct 19) in the NLP section.
  6. Invited talk at Princeton University (Oct 2). Host: Danqi Chen

Research Interests: 

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