Baseline Models for Pronoun Prediction and Pronoun-Aware Translation

Abstract

This paper presents baseline models for the cross-lingual pronoun prediction task and the pronoun-focused translation task at DiscoMT 2015. We present simple yet effective classifiers for the former and discuss the impact of various contextual features on the prediction performance. In the translation task we rely on the document-level decoder Docent and a cross-sentence target language-model over selected words based on the parts-of-speech of the aligned source language words.