Domain adaptation challenges of BERT in tokenization and sub-word representations of Out-of-Vocabulary words

Anmol Nayak, Hariprasad Timmapathini, Karthikeyan Ponnalagu, Vijendran Gopalan Venkoparao. Domain adaptation challenges of BERT in tokenization and sub-word representations of Out-of-Vocabulary words. In Anna Rogers, João Sedoc, Anna Rumshisky, editors, Proceedings of the First Workshop on Insights from Negative Results in NLP, Insights 2020, Online, November 19, 2020. pages 1-5, Association for Computational Linguistics, 2020. [doi]

Abstract

Abstract is missing.