LIUM Machine Translation Systems for WMT17 News Translation Task

By Mercedes García-Martínez, Ozan Caglayan, Walid Aransa, Adrien Bardet, Fethi Bougares, Loïc Barrault. 2017

15 citations recorded by the source corpus.

This paper describes LIUM submissions to WMT17 News Translation Task for English-German, English-Turkish, English-Czech and English-Latvian language pairs. We train BPE-based attentive Neural Machine Translation systems with and without factored outputs using the open source nmtpy framework. Competitive scores were obtained by ensembling various systems and exploiting the availability of target monolingual corpora for back-translation. The impact of back-translation quantity and quality is also analyzed for English-Turkish where our post-deadline submission surpassed the best entry by +1.6 BLEU.

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

Findings of the 2017 Conference on Machine Translation (WMT17) (2017, background): “LIUM-CVC University of Le Mans / Universitat Autonoma de Barcelona (Garcı́a-Martı́nez et al., 2017)”
Towards Interlingua Neural Machine Translation (2019, unknown): “The performance of the baseline transformer (nonvariational) is almost competitive with the best system results from WMT 2017 (García-Martínez et al. 2017).”
From bilingual to multilingual neural‐based machine translation by incremental training (2019, result): “Note that the performances of both the baseline and our architecture in this second configuration are higher than the best system results from WMT 2017 (García-Martínez et al., 2017).”
Back-Translation Sampling by Targeting Difficult Words in Neural Machine Translation (2018, background): “This approach yields state-of-the-art results even when large parallel data are available and has become common practice in NMT (Sennrich et al., 2017; Garcı́a-Martı́nez et al., 2017; Ha et al., 2017).”
(Self-Attentive) Autoencoder-based Universal Language Representation for Machine Translation (2018, unknown): “The performance of the baseline transformer (nonvariational) is almost competitive with the best system results from WMT 2017 (Garcı́a-Martı́nez et al., 2017).”