Adapting to the Long Tail: A Meta-Analysis of Transfer Learning Research for Language Understanding Tasks

TL;DR

This paper conducts a meta-analysis of transfer learning research in natural language understanding, focusing on how well current methods address the long tail of infrequent phenomena and identifying future research directions.

Contribution

It introduces a meta-analysis framework to evaluate transfer learning methods for the long tail in NLU and provides insights from a case study on clinical narratives.

Findings

Transfer learning studies target diverse long tail dimensions.

Certain adaptation properties improve long tail performance.

Identifies methodological gaps impacting long tail results.

Abstract

Natural language understanding (NLU) has made massive progress driven by large benchmarks, but benchmarks often leave a long tail of infrequent phenomena underrepresented. We reflect on the question: have transfer learning methods sufficiently addressed the poor performance of benchmark-trained models on the long tail? We conceptualize the long tail using macro-level dimensions (e.g., underrepresented genres, topics, etc.), and perform a qualitative meta-analysis of 100 representative papers on transfer learning research for NLU. Our analysis asks three questions: (i) Which long tail dimensions do transfer learning studies target? (ii) Which properties of adaptation methods help improve performance on the long tail? (iii) Which methodological gaps have greatest negative impact on long tail performance? Our answers highlight major avenues for future research in transfer learning for the long tail. Lastly, using our meta-analysis framework, we perform a case study comparing the performance of various adaptation methods on clinical narratives, which provides interesting insights that may enable us to make progress along these future avenues.