A Word Clustering Approach to Domain Adaptation: Robust parsing of source and target domains

Abstract : We present a technique to improve out-of-domain statistical parsing by reducing lexical data sparseness in a PCFG-LA architecture. We replace ter- minal symbols with unsupervised word clusters acquired from a large news- paper corpus augmented with target-domain data. We also investigate the impact of guiding out-of-domain parsing with predicted part-of-speech tags. We provide an evaluation for French, and obtain improvements in perfor- mance for both non-technical and technical target domains. Though the im- provements over a strong baseline are slight, an interesting result is that the proposed techniques also improve parsing performance on the source do- main, contrary to techniques such as self-training, thus leading to a more ro- bust parser overall. We also describe new target domain evaluation treebanks, freely available, that comprise a total of about 3,000 annotated sentences from the medical domain, regional newspaper articles, French Europarl and French Wikipedia.
Document type :
Journal articles
Complete list of metadatas

https://hal.inria.fr/hal-00940224
Contributor : Djamé Seddah <>
Submitted on : Friday, January 31, 2014 - 3:52:42 PM
Last modification on : Thursday, April 4, 2019 - 1:32:47 AM

Identifiers

Citation

Djamé Seddah, Marie Candito, Enrique Henestroza Anguiano, Henestroza Anguiano Enrique. A Word Clustering Approach to Domain Adaptation: Robust parsing of source and target domains. Journal of Logic and Computation, Oxford University Press (OUP), 2013, ⟨10.1093/logcom/exs082⟩. ⟨hal-00940224⟩

Share

Metrics

Record views

214