The CMU Machine Translation Systems at WMT 2014

By Austin Matthews, Bridger Waleed Ammar, Archna Bhatia, Wes Feely, Greg Hanneman, Eva Schlinger, Swabha Swayamdipta, Yulia Tsvetkov, Alon Lavie, Chris Dyer. 2014

14 citations recorded by the source corpus.

We describe the CMU systems submitted to the 2014 WMT shared translation task. We participated in two language pairs, German–English and Hindi–English. Our innovations include: a label coarsening scheme for syntactic tree-to-tree translation, a host of new discriminative features, several modules to create “synthetic translation options” that can generalize beyond what is directly observed in the training data, and a method of combining the output of multiple word aligners to uncover extra phrase pairs and grammar rules.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Machine Translation

How researchers see this paper

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

In Artificial Intelligence

1. Karin Sim Smith
2. David Steele
3. Lucia Specia
4. Varvara Logacheva
5. Desmond Elliott
6. Loïc Barrault
7. Graham Neubig
8. Ondrej Bojar

In Computer Vision and Pattern Recognition

1. Lucia Specia
2. Desmond Elliott
3. Loïc Barrault

In Machine Translation

1. Lucia Specia
2. Karin Sim Smith
3. Kashif Shah
4. Trevor Cohn
5. Daniel Beck
6. Varvara Logacheva
7. Frédéric Blain

Citations in the corpus

• Sheffield Systems for the Finnish-English WMT Translation Task (2015, background): “Another approach, used by Ammar et al. (2013) is that of synthetic translation options , supple-menting the phrase tables to compensate for the sparseness in translating from/to highly inflected languages.”