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.
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