Assessing the Corpus Size vs. Similarity Trade-off for Word Embeddings in Clinical NLP

Kirk Roberts


Abstract
The proliferation of deep learning methods in natural language processing (NLP) and the large amounts of data they often require stands in stark contrast to the relatively data-poor clinical NLP domain. In particular, large text corpora are necessary to build high-quality word embeddings, yet often large corpora that are suitably representative of the target clinical data are unavailable. This forces a choice between building embeddings from small clinical corpora and less representative, larger corpora. This paper explores this trade-off, as well as intermediate compromise solutions. Two standard clinical NLP tasks (the i2b2 2010 concept and assertion tasks) are evaluated with commonly used deep learning models (recurrent neural networks and convolutional neural networks) using a set of six corpora ranging from the target i2b2 data to large open-domain datasets. While combinations of corpora are generally found to work best, the single-best corpus is generally task-dependent.
Anthology ID:
W16-4208
Volume:
Proceedings of the Clinical Natural Language Processing Workshop (ClinicalNLP)
Month:
December
Year:
2016
Address:
Osaka, Japan
Editors:
Anna Rumshisky, Kirk Roberts, Steven Bethard, Tristan Naumann
Venue:
ClinicalNLP
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
54–63
Language:
URL:
https://aclanthology.org/W16-4208
DOI:
Bibkey:
Cite (ACL):
Kirk Roberts. 2016. Assessing the Corpus Size vs. Similarity Trade-off for Word Embeddings in Clinical NLP. In Proceedings of the Clinical Natural Language Processing Workshop (ClinicalNLP), pages 54–63, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
Assessing the Corpus Size vs. Similarity Trade-off for Word Embeddings in Clinical NLP (Roberts, ClinicalNLP 2016)
Copy Citation:
PDF:
https://aclanthology.org/W16-4208.pdf