Multi-task learning aims at combining information across tasks to boost prediction performance, especially when the number of training samples is small and the number of predictor...
In Minimum Error Rate Training (MERT), BLEU is often used as the error function, despite the fact that it has been shown to have a lower correlation with human judgment than other...
Recent advances in statistical machine translation have used approximate beam search for NP-complete inference within probabilistic translation models. We present an alternative ap...
Abhishek Arun, Barry Haddow, Philipp Koehn, Adam L...
Phrase-based decoding is conceptually simple and straightforward to implement, at the cost of drastically oversimplified reordering models. Syntactically aware models make it pos...
Recent work in the field of machine translation (MT) evaluation suggests that sentence level evaluation based on machine learning (ML) can outperform the standard metrics such as B...
Antoine Veillard, Elvina Melissa, Cassandra Theodo...