Guiding Neural Machine Translation with Retrieved Translation Pieces

Zhang, Jingyi; Utiyama, Masao; Sumita, Eiichro; Neubig, Graham; Nakamura, Satoshi

doi:10.48550/arxiv.1804.02559

Cited by 13 publications

(10 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Edit distance is a way of quantifying how dissimilar two strings are by counting the minimum number of operations required to transform one string into the other [34]. To normalise the edit distance, we use the following formula which has also been adopted in previous work [17,49].…”

Section: Consistency Metricsmentioning

confidence: 99%

Automatic testing and improvement of machine translation

Sun

Zhang

Harman

et al. 2020

Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering

View full text Add to dashboard Cite

This paper presents TransRepair, a fully automatic approach for testing and repairing the consistency of machine translation systems. TransRepair combines mutation with metamorphic testing to detect inconsistency bugs (without access to human oracles). It then adopts probability-reference or cross-reference to post-process the translations, in a grey-box or black-box manner, to repair the inconsistencies. Our evaluation on two state-of-the-art translators, Google Translate and Transformer, indicates that TransRepair has a high precision (99%) on generating input pairs with consistent translations. With these tests, using automatic consistency metrics and manual assessment, we find that Google Translate and Transformer have approximately 36% and 40% inconsistency bugs. Black-box repair fixes 28% and 19% bugs on average for Google Translate and Transformer. Grey-box repair fixes 30% bugs on average for Transformer. Manual inspection indicates that the translations repaired by our approach improve consistency in 87% of cases (degrading it in 2%), and that our repairs have better translation acceptability in 27% of the cases (worse in 8%).

show abstract

Section: Consistency Metricsmentioning

confidence: 99%

Automatic testing and improvement of machine translation

Sun

Zhang

Harman

et al. 2020

Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering

View full text Add to dashboard Cite

show abstract

“…Another approach presented for NMT improvement was attaching rewards to the retrieved matches of tokens or translation pieces that guided NMT output. A recent technique that employed token-level retrieval for augmenting the decoder of MT system has been presented in [41]. This work offered the advantage of detecting relevant matches for each individual word instead of detecting sentence level matches.…”

Section: Related Workmentioning

confidence: 99%

Deep Searching Based Optimized Machine Translation for Language Translation Tool

Velmurugan¹,

Sumathy²,

Pradeep

2022

Preprint

View full text Add to dashboard Cite

Fuzzy matching techniques are the presently used methods in translating the words. Neural machine translation and statistical machine translation are the methods used in MT. In machine translator tool, the strategy employed for translation needs to handle large amount of datasets and therefore the performance in retrieving correct matching output can be affected. In order to improve the matching score of MT, the advanced techniques can be presented by modifying the existing fuzzy based translator and neural machine translator. The conventional process of modifying architectures and encoding schemes are tedious process. Similarly the preprocessing of datasets also involves more time consumption and memory utilization. In this paper, a new spider web based searching enhanced translation is presented to be employed with the neural machine translator. The proposed scheme enables deep searching of available dataset to detect the accurate matching result. In addition, the quality of translation is improved by presenting an optimal selection scheme for using the sentence matches in source augmentation. The matches retrieved using various matching scores are applied to an optimization algorithm. The source augmentation using optimal retrieved matches increases the translation quality. Further, the selection of optimal match combination helps to reduce time requirement, since it is not necessary to test all retrieved matches in finding target sentence. The performance of translation is validated by measuring the quality of translation using BLEU score. The results are evaluated and compared with other available NMT methods to validate the work.

show abstract

“…For neural MT systems, Zhang et al (2018) retrieves target n-grams to up-weight the reference probabilities. Bapna and Firat (2019) attend over neighbors similar to n-grams in the source using gated attention (Cao and Xiong, 2018).…”

Section: Related Workmentioning

confidence: 99%

Faster Nearest Neighbor Machine Translation

Wang¹,

Li²,

Meng³

et al. 2021

Preprint

View full text Add to dashboard Cite

kNN based neural machine translation (kNN-MT) has achieved state-of-the-art results in a variety of MT tasks. One significant shortcoming of kNN-MT lies in its inefficiency in identifying the k nearest neighbors of the query representation from the entire datastore, which is prohibitively time-intensive when the datastore size is large.In this work, we propose Faster kNN-MT to address this issue. The core idea of Faster kNN-MT is to use a hierarchical clustering strategy to approximate the distance between the query and a data point in the datastore, which is decomposed into two parts: the distance between the query and the center of the cluster that the data point belongs to, and the distance between the data point and the cluster center. We propose practical ways to compute these two parts in a significantly faster manner. Through extensive experiments on different MT benchmarks, we show that Faster kNN-MT is faster than Fast kNN- MT (Meng et al., 2021a) and only slightly (1.2 times) slower than its vanilla counterpart, while preserving model performance as kNN-MT. Faster kNN-MT enables the deployment of kNN-MT models on real-world MT services.

show abstract

Guiding Neural Machine Translation with Retrieved Translation Pieces

Cited by 13 publications

References 10 publications

Automatic testing and improvement of machine translation

Automatic testing and improvement of machine translation

Deep Searching Based Optimized Machine Translation for Language Translation Tool

Faster Nearest Neighbor Machine Translation

Contact Info

Product

Resources

About