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

Djamé Seddah (1, 2) , Marie Candito (1) , Enrique Henestroza Anguiano (1) , Henestroza Anguiano Enrique (1)

1 ALPAGE - Analyse Linguistique Profonde à Grande Echelle ; Large-scale deep linguistic processing
2 UP4 - Université Paris-Sorbonne

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.

Mots clés: Out of domain and morphologically-rich languages statistical parsing; unsupervized word clustering data driven lemmatization; treebanking; biomedical; self training

Domaines: Traitement du texte et du document

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, 2013, ⟨10.1093/logcom/exs082⟩. ⟨hal-00940224⟩