A Word Clustering Approach to Domain Adaptation: Effective Parsing of Biomedical Texts

Abstract : We present a simple and effective way to perform out-of-domain statistical parsing by drastically reducing lexical data sparseness in a PCFG-LA architecture. We replace terminal symbols with unsupervised word clusters acquired from a large newspaper corpus augmented with biomedical target- domain data. The resulting clusters are effective in bridging the lexical gap between source-domain and target-domain vocabularies. Our experiments combine known self-training techniques with unsupervised word clustering and produce promising results, achieving an error reduction of 21% on a new evaluation set for biomedical text with manual bracketing annotations.
Document type :
Conference papers
Complete list of metadatas

Cited literature [21 references]  Display  Hide  Download

https://hal.inria.fr/hal-00659577
Contributor : Marie Candito <>
Submitted on : Friday, January 13, 2012 - 10:38:57 AM
Last modification on : Friday, May 3, 2019 - 1:41:49 AM
Long-term archiving on : Saturday, April 14, 2012 - 2:22:50 AM

File

IWPT2011-candito_henestro_sedd...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00659577, version 1

Citation

Marie Candito, Enrique Henestroza Anguiano, Djamé Seddah. A Word Clustering Approach to Domain Adaptation: Effective Parsing of Biomedical Texts. IWPT'11 - 12th International Conference on Parsing Technologies, Oct 2011, Dublin, Ireland. ⟨hal-00659577⟩

Share

Metrics

Record views

308

Files downloads

271