Abu-MaTran at WMT 2016 Translation Task: Deep Learning, Morphological Segmentation and Tuning on Character Sequences

By Víctor M. Sánchez-Cartagena, Antonio Toral. 2016

26 citations recorded by the source corpus.

This paper presents the systems submitted by the Abu-MaTran project to the Englishto-Finnish language pair at the WMT 2016 news translation task. We applied morphological segmentation and deep learning in order to address (i) the data scarcity problem caused by the lack of in-domain parallel data in the constrained task and (ii) the complex morphology of Finnish. We submitted a neural machine translation system, a statistical machine translation system reranked with a neural language model and the combination of their outputs tuned on character sequences. The combination and the neural system were ranked first and second respectively according to automatic evaluation metrics and tied for the first place in the human evaluation.

Subfields: Artificial Intelligence

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

Citations in the corpus

chrF++: words helping character n-grams (2017, methodology): “Since there is almost no difference between 2 and 3, and putting too much weight to recall could jeopardise some other applications such as system tuning or system combination (for example, (Sánchez-Cartagena and Toral, 2016) decided to use CHRF1 because CHRF3 lead to generation of too long sentence”
Linguistically Motivated Vocabulary Reduction for Neural Machine Translation from Turkish to English (2017, methodology): “ words but can only reduce the vocabulary to a limited extent, usually by applying cut-oﬀ thresholds on the vocabulary and reducing the coverage of the long tail of less frequent words. For instance, Sánchez-Cartagena and Toral (2016) have used a morphological analyzer to separate words into root an”
A Multifaceted Evaluation of Neural versus Phrase-Based Machine Translation for 9 Language Directions (2017, methodology): “Word segmentation is carried out with the help of a lexicon in the EN→FI direction (Sánchez-Cartagena and Toral, 2016) and in an unsupervised way in the remaining directions (Sennrich et al.”