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

Aakanksha Naik, Jill Lehman, Carolyn Rosé


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 (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.
Anthology ID:
2022.tacl-1.56
Volume:
Transactions of the Association for Computational Linguistics, Volume 10
Month:
Year:
2022
Address:
Cambridge, MA
Editors:
Brian Roark, Ani Nenkova
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
956–980
Language:
URL:
https://aclanthology.org/2022.tacl-1.56
DOI:
10.1162/tacl_a_00500
Bibkey:
Cite (ACL):
Aakanksha Naik, Jill Lehman, and Carolyn Rosé. 2022. Adapting to the Long Tail: A Meta-Analysis of Transfer Learning Research for Language Understanding Tasks. Transactions of the Association for Computational Linguistics, 10:956–980.
Cite (Informal):
Adapting to the Long Tail: A Meta-Analysis of Transfer Learning Research for Language Understanding Tasks (Naik et al., TACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.tacl-1.56.pdf