Abstract

State-of-the-art statistical parsers and POS taggers perform very well when trained with large amounts of in-domain data. When training data is out-of-domain or limited, accuracy degrades. In this work, we aim to compensate for the lack of available training data by exploiting similarities between test set sentences. We show how to augment sentence level models for parsing and POS tagging with inter-sentence consistency constraints. To deal with the resulting global objective, we present an efficient and exact dual decomposition decoding algorithm. In experiments, we add consistency constraints to the MST parser and the Stanford part-of-speech tagger and demonstrate significant error reduction in the domain adaptation and the lightly supervised settings across five languages.

Joint work with Alexander Rush, Michael Collins and Amir Globerson