CUNI submission in WMT17: Chimera goes neural

Sudarikov, Roman; Mareċek, David; Kocmi, Tom; Variš, Dušan; Bojar, Ondřej

doi:10.18653/v1/w17-4720

Cited by 4 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…During my doctoral study, we investigated the use of curriculum learning (Kocmi and Bojar, 2017a), helped to prepare a Neural Training Shared Task at WMT 2017 , and developed a neural abstractive summarization tool (Straka et al, 2018). Furthermore, we participated in several shared tasks (Bojar et al, 2016b;Sudarikov et al, 2017;Kocmi et al, , 2018aKocmi and Bojar, 2019b).…”

Section: Contributionsmentioning

confidence: 99%

Trivial Transfer Learning for Low-Resource Neural Machine Translation

Kocmi¹,

Bojar²

2018

Proceedings of the Third Conference on Machine Translation: Research Papers

Self Cite

128

View full text Add to dashboard Cite

Transfer learning has been proven as an effective technique for neural machine translation under low-resource conditions. Existing methods require a common target language, language relatedness, or specific training tricks and regimes. We present a simple transfer learning method, where we first train a "parent" model for a high-resource language pair and then continue the training on a lowresource pair only by replacing the training corpus. This "child" model performs significantly better than the baseline trained for lowresource pair only. We are the first to show this for targeting different languages, and we observe the improvements even for unrelated languages with different alphabets.

show abstract

Section: Contributionsmentioning

confidence: 99%

Trivial Transfer Learning for Low-Resource Neural Machine Translation

Kocmi¹,

Bojar²

2018

Proceedings of the Third Conference on Machine Translation: Research Papers

Self Cite

128

View full text Add to dashboard Cite

show abstract

“…MERT was run on the WMT16 test set. Further details on experiments with different combinations of phrase tables are available in Sudarikov et al (2017).…”

Section: Chimera Descriptionmentioning

confidence: 99%

“…For English-Czech models, we used the same datasets as described in Sudarikov et al (2017). First we took Czech monolingual news corpus, which was translated into English using Nematus (Sennrich et al, 2017) model, with 59 million sentences.…”

Section: Data Preparationmentioning

confidence: 99%

“…For English-Czech translation task, we took the same system combination setup as described in Sudarikov et al (2017). We used outputs of three different individual forward translation systems, trained on a synthetic backtranslated training dataset and combined them into the final output.…”

Section: Chimera Descriptionmentioning

confidence: 99%

“…Our last language pair of interest is English to Czech translation, where we use our last year's model Sudarikov et al (2017) for comparison purposes. The system is based on a hybrid combination of phrase-based, transfer-based and NMT approaches.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

CUNI Submissions in WMT18

Kocmi¹,

Sudarikov²,

Bojar³

2018

Proceedings of the Third Conference on Machine Translation: Shared Task Papers

Self Cite

View full text Add to dashboard Cite

We participated in the WMT 2018 shared news translation task in three language pairs: English-Estonian, English-Finnish, and English-Czech. Our main focus was the lowresource language pair of Estonian and English for which we utilized Finnish parallel data in a simple method. We first train a "parent model" for the high-resource language pair followed by adaptation on the related lowresource language pair. This approach brings a substantial performance boost over the baseline system trained only on Estonian-English parallel data. Our systems are based on the Transformer architecture. For the English to Czech translation, we have evaluated our last year models of hybrid phrase-based approach and neural machine translation mainly for comparison purposes.

show abstract

Evaluating the morphological competence of Machine Translation Systems

Burlot¹,

Yvon²

2017

Proceedings of the Second Conference on Machine Translation

View full text Add to dashboard Cite

While recent changes in Machine Translation state-of-the-art brought translation quality a step further, it is regularly acknowledged that the standard automatic metrics do not provide enough insights to fully measure the impact of neural models. This paper proposes a new type of evaluation focused specifically on the morphological competence of a system with respect to various grammatical phenomena. Our approach uses automatically generated pairs of source sentences, where each pair tests one morphological contrast. This methodology is used to compare several systems submitted at WMT'17 for English into Czech and Latvian.

show abstract

CUNI submission in WMT17: Chimera goes neural

Cited by 4 publications

References 13 publications

Trivial Transfer Learning for Low-Resource Neural Machine Translation

Trivial Transfer Learning for Low-Resource Neural Machine Translation

CUNI Submissions in WMT18

Evaluating the morphological competence of Machine Translation Systems

Contact Info

Product

Resources

About