Data point selection for cross-language adaptation of dependency parsers

TY - GEN

T1 - Data point selection for cross-language adaptation of dependency parsers

AU - Søgaard, Anders

PY - 2011

Y1 - 2011

N2 - We consider a very simple, yet effective, approach to cross language adaptation of dependency parsers. We first remove lexical items from the treebanks and map part-of-speech tags into a common tagset. We then train a languagemodel on tag sequences in otherwise unlabeled target data and rank labeled source data by perplexity per word of tag sequences from less similar to most similar to the target. We then train our target language parser on the most similar data points in the source labeled data. The strategy achieves much better results than a non-adapted baseline and state-of-the-art unsupervised dependency parsing, and results are comparable to more complex projection-based cross language adaptation algorithms.

AB - We consider a very simple, yet effective, approach to cross language adaptation of dependency parsers. We first remove lexical items from the treebanks and map part-of-speech tags into a common tagset. We then train a languagemodel on tag sequences in otherwise unlabeled target data and rank labeled source data by perplexity per word of tag sequences from less similar to most similar to the target. We then train our target language parser on the most similar data points in the source labeled data. The strategy achieves much better results than a non-adapted baseline and state-of-the-art unsupervised dependency parsing, and results are comparable to more complex projection-based cross language adaptation algorithms.

M3 - Article in proceedings

BT - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-HLT)

PB - Association for Computational Linguistics

ER -