We present a maximum entropy classifier for cross-lingual pronoun prediction. The features are based on local source- and target-side contexts and antecedent information obtained by a co-reference resolution system. With only a small set of feature types our best performing system achieves an accuracy of 72.31%. According to the shared task’s official macro- averaged F1-score at 57.07%, we are among the top systems, at position three out of 14. Feature ablation results show the important role of target-side information in general and of the resolved target-side antecedent in particular for predicting the correct classes.
|Title of host publication||Proceedings of the Second Workshop on Discourse in Machine Translation|
|Place of Publication||Lisbon, Portugal|
|Publisher||Association for Computational Linguistics|
|Number of pages||7|
|Publication status||Published - 1 Sep 2015|