A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf
.
Getting BART to Ride the Idiomatic Train: Learning to Represent Idiomatic Expressions
[article]
2022
arXiv
pre-print
Idiomatic expressions (IEs), characterized by their non-compositionality, are an important part of natural language. They have been a classical challenge to NLP, including pre-trained language models that drive today's state-of-the-art. Prior work has identified deficiencies in their contextualized representation stemming from the underlying compositional paradigm of representation. In this work, we take a first-principles approach to build idiomaticity into BART using an adapter as a
arXiv:2207.03679v1
fatcat:3t3duneexjcbhjfs6pst567vnq