Language Model is All You Need: Natural Language Understanding as Question Answering

TL;DR

This paper demonstrates that framing natural language understanding as question answering significantly improves performance in low-data scenarios and can be enhanced through sequential transfer learning across domains.

Contribution

The study introduces a transfer learning approach that maps NLU tasks to QA problems, achieving up to tenfold data efficiency improvements.

Findings

Significant performance gains in low-data regimes.

Sequential transfer learning enhances NLU across domains.

Data reduction by up to a factor of 10.

Abstract

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 specific family of transfer learning, where the target domain is mapped to the source domain. Specifically we map Natural Language Understanding (NLU) problems to QuestionAnswering (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.