Cross-lingual Pronoun Prediction for English, French and German with Maximum Entropy Classification

Abstract

We present our submission to the crosslingual pronoun prediction (CLPP) shared task for English-German and English- French at the First Conference on Machine Translation (WMT16). We trained a Maximum Entropy (MaxEnt) classifier based on features from Wetzel et al. (2015), that we adapted to the new task and applied to a new language pair. Additional features such as n-grams of the pronoun context and prediction of NULLtranslations proved helpful to a varying degree. Experiments with a sequence classifier over pronoun sequences did not show any improvements. Our submission is among the top three systems for English-French (61.62% macro-averaged recall) and in the middle range for English- German (48.72%) out of nine submissions.