A Document-Level SMT System with Integrated Pronoun Prediction
Christian Hardmeier · 2015
This paper describes one of Uppsala University's submissions to the pronounfocused machine translation (MT) shared task at DiscoMT 2015.The system is based on phrase-based statistical MT implemented with the document-level decoder Docent.It includes a neural network for pronoun prediction trained with latent anaphora resolution.At translation time, coreference information is obtained from the Stanford CoreNLP system.