YSDA Participation in the WMT'16 Quality Estimation Shared Task

Kozlova, Anna; Shmatova, Mariya; Frolov, Anton

doi:10.18653/v1/w16-2385

Cited by 21 publications

(16 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Along with the features produced by the Bilingual Expert model, we extract another 17 QE baseline features for the sentence-level task using QuEst++ and additional resources (source and target corpora, language models, ngram counts and lexical translation tables) provided on the WMT18 QE website 2 . Kozlova et al (2016) verifies the significance of these features using Random Forest (Breiman, 2001). Four of them are the most crucial among all according to their degrees of importance.…”

Section: Human-crafted Featuresmentioning

confidence: 94%

Alibaba Submission for WMT18 Quality Estimation Task

Wang¹,

Fan²,

Li³

et al. 2018

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

View full text Add to dashboard Cite

The goal of WMT 2018 Shared Task on Translation Quality Estimation is to investigate automatic methods for estimating the quality of machine translation results without reference translations. This paper presents the QE Brain system, which proposes the neural Bilingual Expert model as a feature extractor based on conditional target language model with a bidirectional transformer and then processes the semantic representations of source and the translation output with a Bi-LSTM predictive model for automatic quality estimation. The system has been applied to the sentence-level scoring and ranking tasks as well as the wordlevel tasks for finding errors for each word in translations. An extensive set of experimental results have shown that our system outperformed the best results in WMT 2017 Quality Estimation tasks and obtained top results in WMT 2018. * * indicates equal contribution.

show abstract

Section: Human-crafted Featuresmentioning

confidence: 94%

Alibaba Submission for WMT18 Quality Estimation Task

Wang¹,

Fan²,

Li³

et al. 2018

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

View full text Add to dashboard Cite

show abstract

“…• number of tokens about punctuation in the source sentence and the translation (Kozlova et al, 2016) and the cosine between them.…”

Section: Referential Translation Machinesmentioning

confidence: 99%

Predicting Translation Performance with Referential Translation Machines

Biçici¹

2017

Proceedings of the Second Conference on Machine Translation

View full text Add to dashboard Cite

Referential translation machines achieve top performance in both bilingual and monolingual settings without accessing any task or domain specific information or resource. RTMs achieve the 3rd system results for German to English sentence-level prediction of translation quality and the 2nd system results according to root mean squared error. In addition to the new features about substring distances, punctuation tokens, character n-grams, and alignment crossings, and additional learning models, we average prediction scores from different models using weights based on their training performance for improved results.

show abstract

“…We complement character-level information with engineered features, given that the most effective QE and EIA methods in previous work heavily exploit them (Kim and Lee, 2016;Kozlova et al, 2016;Refaee and Rieser, 2016;Wang et al, 2016). To do so, we apply a simple multi-layer perceptron (MLP) over a set of input engineered features.…”

Section: Incorporating Engineered Featuresmentioning

confidence: 99%

Feature-Enriched Character-Level Convolutions for Text Regression

Paetzold¹,

Specia²

2017

Proceedings of the Second Conference on Machine Translation

View full text Add to dashboard Cite

We present a new model for text regression that seamlessly combine engineered features and character-level information through deep parallel convolution stacks, multi-layer perceptrons and multitask learning. We use these models to create the SHEF/CNN systems for the sentence-level Quality Estimation task of WMT 2017 and Emotion Intensity Analysis task of WASSA 2017. Our experiments reveal that combining character-level clues and engineered features offers noticeable performance improvements over using only one of these sources of information in isolation.

show abstract

YSDA Participation in the WMT'16 Quality Estimation Shared Task

Cited by 21 publications

References 5 publications

Alibaba Submission for WMT18 Quality Estimation Task

Alibaba Submission for WMT18 Quality Estimation Task

Predicting Translation Performance with Referential Translation Machines

Feature-Enriched Character-Level Convolutions for Text Regression

Contact Info

Product

Resources

About