Target Language Adaptation of Discriminative Transfer Parsers

Täckström, Oscar and McDonald, Ryan and Nivre, Joakim (2013) Target Language Adaptation of Discriminative Transfer Parsers. In: The 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 10-12 June 2013, Atlanta, GA, USA. (In Press)

PDF - Accepted Version


We study multi-source transfer parsing for resource-poor target languages; specifically methods for target language adaptation of delexicalized discriminative graph-based dependency parsers. We first show how recent insights on selective parameter sharing, based on typological and language-family features, can be applied to a discriminative parser by carefully decomposing its model features. We then show how the parser can be relexicalized and adapted using unlabeled target language data and a learning method that can incorporate diverse knowledge sources through ambiguous labelings. In the latter scenario, we exploit two sources of knowledge: arc marginals derived from the base parser in a self-training algorithm, and arc predictions from multiple transfer parsers in an ensemble-training algorithm. Our final model outperforms the state of the art in multi-source transfer parsing on 15 out of 16 evaluated languages.

Item Type:Conference or Workshop Item (Paper)
ID Code:5501
Deposited By:Oscar Tackström
Deposited On:11 Apr 2013 05:56
Last Modified:12 Apr 2013 15:12

Repository Staff Only: item control page