LIUM’s SMT Machine Translation Systems for WMT 2011

By Christophe Servan, Patrik Lambert, Anthony Rousseau, Holger Schwenk, Loïc Barrault. 2011

15 citations recorded by the source corpus.

Subfields: Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

1. Kyunghyun Cho
2. Yoshua Bengio
3. Quoc V. Le
4. Graham Neubig
5. Mohit Bansal
6. Jianfeng Gao
7. Oriol Vinyals
8. Loïc Barrault

Citations in the corpus

• Sequence to Sequence Learning with Neural Networks (2014, methodology): “We chose this translation task and this spe cific training set subset because of the public availability of a tokenized training and test set tog ether with 1000-best lists from the LIUM SMT baseline [30, 31].”
• LIUM’s SMT Machine Translation Systems for WMT 2012 (2012, methodology): “The main differences with respect to previous year’s system (Schwenk et al., 2011) are as follows: (i) use of more training data as provided by the organizers and (ii) better selection of the monolingual and parallel data according to the domain, using the cross-entropy difference with respect to…”