Language Model is All You Need: Natural Language Understanding as Question Answering
This work addresses data efficiency for NLU applications, though it appears incremental as it adapts existing transfer learning methods to a specific mapping approach.
The authors tackled the problem of Natural Language Understanding (NLU) in low data regimes by mapping NLU tasks to Question Answering (QA) problems, achieving up to a 10x reduction in required data for the same performance.
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.