Guiding Neural Machine Translation Decoding with External Knowledge

Chatterjee, Rajen; Negri, Matteo; Turchi, Marco; Federico, Marcello; Specia, Lucia; Blain, Frédéric

doi:10.18653/v1/w17-4716

Cited by 76 publications

(47 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different prefixes correspond to different decoder states and states are known to capture the remaining length of the translation (Shi et al, 2016). Our method extends over that of Chatterjee et al (2017), which scores constraints only once all necessary information is available in the decoded prefix. The resulting beam search then performs similarly to A* (Hart et al, 1968).…”

Section: Integration Of Dubbing Constraintsmentioning

confidence: 99%

Integration of Dubbing Constraints into Machine Translation

Saboo¹,

Baumann²

2019

Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers)

View full text Add to dashboard Cite

Translation systems aim to perform a meaningpreserving conversion of linguistic material (typically text but also speech) from a source to a target language (and, to a lesser degree, the corresponding socio-cultural contexts). Dubbing, i. e., the lip-synchronous translation and revoicing of speech adds to this constraints about the close matching of phonetic and resulting visemic synchrony characteristics of source and target material. There is an inherent conflict between a translation's meaning preservation and its 'dubbability' and the resulting trade-off can be controlled by weighing the synchrony constraints. We introduce our work, which to the best of our knowledge is the first of its kind, on integrating synchrony constraints into the machine translation paradigm. We present first results for the integration of synchrony constraints into encoder decoder-based neural machine translation and show that considerably more 'dubbable' translations can be achieved with only a small impact on BLEU score, and dubbability improves more steeply than BLEU degrades. * *This work was performed during an internship at Universität Hamburg, Germany.

show abstract

Section: Integration Of Dubbing Constraintsmentioning

confidence: 99%

Integration of Dubbing Constraints into Machine Translation

Saboo¹,

Baumann²

2019

Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers)

View full text Add to dashboard Cite

show abstract

“…This involves an approach capable of simultaneously gathering knowledge from different SW resources for addressing the ambiguity of named entities, which can also alleviate the problem of OOV words. This insight relies on recent works [212,213], which have guided the usage of external knowledge in NMT systems for overcoming the vocabulary limitation of NN models. Also, we aim to create a method to structure natural language sentences into triples for supporting the generation task.…”

Section: Discussionmentioning

confidence: 99%

Machine Translation using Semantic Web Technologies: A Survey

Moussallem

Wauer

Ngomo

2018

Journal of Web Semantics

View full text Add to dashboard Cite

A large number of machine translation approaches have recently been developed to facilitate the fluid migration of content across languages. However, the literature suggests that many obstacles must still be dealt with to achieve better automatic translations. One of these obstacles is lexical and syntactic ambiguity. A promising way of overcoming this problem is using Semantic Web technologies. This article presents the results of a systematic review of machine translation approaches that rely on Semantic Web technologies for translating texts. Overall, our survey suggests that while Semantic Web technologies can enhance the quality of machine translation outputs for various problems, the combination of both is still in its infancy.

show abstract

“…In a closely related work, Chatterjee et al (2017) present an approach that integrates external knowledge into an NMT decoder that prioritizes translation recommendations supplied by a termbank. Hokamp and Liu (2017) present grid beam search, a very general way to integrate external knowledge into a model's output without modifying the model parameters or training data.…”

Section: Related Workmentioning

confidence: 99%

Analysing terminology translation errors in statistical and neural machine translation

Haque

Hasanuzzaman

Way

2020

Machine Translation

View full text Add to dashboard Cite

Terminology translation plays a critical role in domain-specific machine translation (MT). Phrase-based statistical MT (PB-SMT) has been the dominant approach to MT for the past 30 years, both in academia and industry. Neural MT (NMT), an end-to-end learning approach to MT, is steadily taking the place of PB-SMT. In this paper, we conduct comparative qualitative evaluation and comprehensive error analysis on terminology translation in PB-SMT and NMT in two translation directions: English-to-Hindi and Hindi-to-English. To the best of our knowledge, there is no gold standard available for evaluating terminology translation quality in MT. For this reason we select an evaluation test set from a legal domain corpus and create a gold standard for evaluating terminology translation in MT. We also propose an error typology taking the terminology translation errors in MT into consideration. We translate sentences of the test set with our MT systems and terminology translations are manually classified as per the error typology. We evaluate the MT system's performance on terminology translation, and demonstrate our findings, unraveling strengths, weaknesses, and similarities of PB-SMT and NMT in the area of term translation.

show abstract

Guiding Neural Machine Translation Decoding with External Knowledge

Cited by 76 publications

References 23 publications

Integration of Dubbing Constraints into Machine Translation

Integration of Dubbing Constraints into Machine Translation

Machine Translation using Semantic Web Technologies: A Survey

Analysing terminology translation errors in statistical and neural machine translation

Contact Info

Product

Resources

About