Language model is all you need: Natural language understanding as Question answering

Mahdi Namazifar, Alexandros Papangelis, Gokhan Tur, Dilek Hakkani-T¨ur

Research output: Contribution to journalConference articlepeer-review


Different flavors of transfer learning have shown tremendous impact in advancing research and applications of machine learning. In this work we study the use of a certain family of transfer learning, where the target domain is mapped to the source domain. Specifically we map Natural Language Understanding (NLU) problems to Question Answering (QA) problems and we show that in low data regimes this approach offers significant improvements compared to other approaches to NLU. Moreover, we show that these gains could be increased through sequential transfer learning across NLU problems from different domains. We show that our approach could reduce the amount of required data for the same performance by up to a factor of 10.

Original languageEnglish (US)
Pages (from-to)7803-7807
Number of pages5
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
StatePublished - 2021
Externally publishedYes
Event2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Virtual, Toronto, Canada
Duration: Jun 6 2021Jun 11 2021


  • Natural language understanding
  • Question answering
  • Transfer learning

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering


Dive into the research topics of 'Language model is all you need: Natural language understanding as Question answering'. Together they form a unique fingerprint.

Cite this