all AI news
Getting BART to Ride the Idiomatic Train: Learning to Represent Idiomatic Expressions. (arXiv:2207.03679v1 [cs.CL])
July 11, 2022, 1:10 a.m. | Ziheng Zeng, Suma Bhat
cs.LG updates on arXiv.org arxiv.org
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 lightweight non-compositional language expert trained on
idiomatic sentences. The improved capability over baselines (e.g., BART) …
More from arxiv.org / cs.LG updates on arXiv.org
The Perception-Robustness Tradeoff in Deterministic Image Restoration
1 day, 15 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne