QUality Estimation from ScraTCH (QUETCH): Deep Learning for Word-level Translation Quality Estimation

Kreutzer, Julia; Schamoni, Shigehiko; Riezler, Stefan

doi:10.18653/v1/w15-3037

Cited by 60 publications

(52 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to that, six new features were included which contain combinations of other features, and which proved useful in (Kreutzer et al, 2015;Martins et al, 2016):…”

Section: Baseline Systemsmentioning

confidence: 99%

Findings of the WMT 2018 Shared Task on Quality Estimation

Specia¹,

Blain²,

Logacheva³

et al. 2018

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

View full text Add to dashboard Cite

We report the results of the WMT18 shared task on Quality Estimation, i.e. the task of predicting the quality of the output of machine translation systems at various granularity levels: word, phrase, sentence and document. This year we include four language pairs, three text domains, and translations produced by both statistical and neural machine translation systems. Participating teams from ten institutions submitted a variety of systems to different task variants and language pairs.

show abstract

“…In addition to that, six new features were included which contain combinations of other features, and which proved useful in (Kreutzer et al, 2015;Martins et al, 2016):…”

Section: Baseline Systemsmentioning

confidence: 99%

Findings of the WMT 2018 Shared Task on Quality Estimation

Specia¹,

Blain²,

Logacheva³

et al. 2018

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

View full text Add to dashboard Cite

show abstract

“…The system receives as input the source and target sentences s and t, their word-level alignments A, and their corresponding POS tags obtained from TurboTagger. The input layer follows a similar architecture as QUETCH (Kreutzer et al, 2015), with the addition of POS features. A vector representing each target word is obtained by concatenating the embedding of that word with those of the aligned word in the source.…”

Section: Neural Systemmentioning

confidence: 99%

“…If there are multiple aligned source words, they are concatenated into a single feature. Kreutzer et al (2015).…”

Section: Neural Systemmentioning

confidence: 99%

Unbabel's Participation in the WMT17 Translation Quality Estimation Shared Task

Martins¹,

Kepler²,

Monteiro³

2017

Proceedings of the Second Conference on Machine Translation

View full text Add to dashboard Cite

This paper presents the contribution of the Unbabel team to the WMT 2017 Shared Task on Translation Quality Estimation. We participated on the word-level and sentence-level tracks. We describe our two submitted systems: (i) STACKEDQE, a "pure" QE system, trained only on the provided training sets, which is a stacked combination of a feature-rich sequential linear model with a neural network, and (ii) FULLSTACKEDQE, which also stacks the predictions of an automatic post-editing system, trained on additional data. When evaluated on the EnglishGerman and German-English datasets, FULLSTACKEDQE achieved word-level F MULT 1 scores of 56.6% and 52.9%, and sentence-level correlation Pearson scores of 64.1% and 62.6%, respectively. Our system ranked second in both tracks, being statistically indistinguishable from the best system in the word-level track.

show abstract

“…In recent years, NNs have also shown promising results for sentence and word-level QE in different languages and domains (Kreutzer et al, 2015;Patel and Sasikumar, 2016). Moreover, focusing on the detection of grammatical errors from a different perspective, Liu and Liu (2016) proposed to derive positive and negative samples from unlabelled data, by generating grammatical errors artificially, and showed that RNNs outperform Support Vector Machines (SVMs) in judging the grammaticality of each word.…”

Section: Related Workmentioning

confidence: 99%

A Neural Network Architecture for Detecting Grammatical Errors in Statistical Machine Translation

Tezcan¹,

Hoste²,

Macken³

2017

The Prague Bulletin of Mathematical Linguistics

View full text Add to dashboard Cite

In this paper we present a Neural Network (NN) architecture for detecting grammatical errors in Statistical Machine Translation (SMT) using monolingual morpho-syntactic word representations in combination with surface and syntactic context windows. We test our approach on two language pairs and two tasks, namely detecting grammatical errors and predicting overall post-editing effort. Our results show that this approach is not only able to accurately detect grammatical errors but it also performs well as a quality estimation system for predicting overall post-editing effort, which is characterised by all types of MT errors. Furthermore, we show that this approach is portable to other languages.

show abstract

QUality Estimation from ScraTCH (QUETCH): Deep Learning for Word-level Translation Quality Estimation

Cited by 60 publications

References 15 publications

Findings of the WMT 2018 Shared Task on Quality Estimation

Findings of the WMT 2018 Shared Task on Quality Estimation

Unbabel's Participation in the WMT17 Translation Quality Estimation Shared Task

A Neural Network Architecture for Detecting Grammatical Errors in Statistical Machine Translation

Contact Info

Product

Resources

About