Cross-lingual Pronoun Prediction with Linguistically Informed Features

Abstract

We present the LIMSI's cross-lingual pronoun prediction system for the WMT 2016 shared task. We use high-level linguistic features with explicit coreference resolution and expletive detection and rely on dependency annotations and a morphological lexicon. We show that our few, carefully chosen features perform significantly better than several language model baselines and competitively compared to the other systems submitted.