Evaluation of Terminology Translation in Instance-Based Neural MT Adaptation

Please use this identifier to cite or link to this item: http://hdl.handle.net/10045/76037
Información del item - Informació de l'item - Item information
Title: Evaluation of Terminology Translation in Instance-Based Neural MT Adaptation
Authors: Farajian, M. Amin | Bertoldi, Nicola | Negri, Matteo | Turchi, Marco | Federico, Marcello
Keywords: Machine Translation
Knowledge Area: Lenguajes y Sistemas Informáticos
Issue Date: 2018
Publisher: European Association for Machine Translation
Citation: Farajian, M. Amin, et al. “Evaluation of Terminology Translation in Instance-Based Neural MT Adaptation”. In: Pérez-Ortiz, Juan Antonio, et al. (Eds.). Proceedings of the 21st Annual Conference of the European Association for Machine Translation: 28-30 May 2018, Universitat d'Alacant, Alacant, Spain, pp. 149-158
Abstract: We address the issues arising when a neural machine translation engine trained on generic data receives requests from a new domain that contains many specific technical terms. Given training data of the new domain, we consider two alternative methods to adapt the generic system: corpus-based and instance-based adaptation. While the first approach is computationally more intensive in generating a domain-customized network, the latter operates more efficiently at translation time and can handle on-the-fly adaptation to multiple domains. Besides evaluating the generic and the adapted networks with conventional translation quality metrics, in this paper we focus on their ability to properly handle domain-specific terms. We show that instance-based adaptation, by fine-tuning the model on-the-fly, is capable to significantly boost the accuracy of translated terms, producing translations of quality comparable to the expensive corpus-based method.
Sponsor: This work has been partially supported by the EC-funded H2020 projects QT21 (grant no. 645452) and ModernMT (grant no. 645487). This work was also supported by The Alan Turing Institute under the EPSRC grant EP/N510129/1 and by a donation of Azure credits by Microsoft.
URI: http://hdl.handle.net/10045/76037
ISBN: 978-84-09-01901-4
Language: eng
Type: info:eu-repo/semantics/conferenceObject
Rights: © 2018 The authors. This article is licensed under a Creative Commons 3.0 licence, no derivative works, attribution, CC-BY-ND.
Peer Review: si
Publisher version: http://eamt2018.dlsi.ua.es/proceedings-eamt2018.pdf
Appears in Collections:Congresos - EAMT2018 - Proceedings
Research funded by the EU

Files in This Item:
Files in This Item:
File Description SizeFormat 
ThumbnailEAMT2018-Proceedings_17.pdf1,61 MBAdobe PDFOpen Preview

This item is licensed under a Creative Commons License Creative Commons