English

Word Embeddings for Chemical Patent Natural Language Processing

Computation and Language 2020-10-27 v1 Machine Learning

Abstract

We evaluate chemical patent word embeddings against known biomedical embeddings and show that they outperform the latter extrinsically and intrinsically. We also show that using contextualized embeddings can induce predictive models of reasonable performance for this domain over a relatively small gold standard.

Keywords

Cite

@article{arxiv.2010.12912,
  title  = {Word Embeddings for Chemical Patent Natural Language Processing},
  author = {Camilo Thorne and Saber Akhondi},
  journal= {arXiv preprint arXiv:2010.12912},
  year   = {2020}
}

Comments

Extended version of an extended abstract presented (and reviewed) at the Latinx Workshop at ICML 2020

R2 v1 2026-06-23T19:37:04.124Z