Institutions | About Us | Help | Gaeilge
rian logo


Mark
Go Back
Syntax-informed interactive neural machine translation
Gupta, Kamal Kumar; Haque, Rejwanul; Ekbal, Asif; Bhattacharyya, Pushpak; Way, Andy
In interactive machine translation (MT), human translators correct errors in automatic translations in collaboration with the MT systems, and this is an effective way to improve productivity gain in translation. Phrase-based statistical MT (PB-SMT) has been the mainstream approach to MT for the past 30 years, both in academia and industry. Neural MT (NMT), an end-to-end learning approach to MT, represents the current state-of-the-art in MT research. The recent studies on interactive MT have indicated that NMT can significantly outperform PB-SMT. In this work, first we investigate the possibility of integrating lexical syntactic descriptions in the form of supertags into the state-of-the-art NMT model, Transformer. Then, we explore whether integration of supertags into Transformer could indeed reduce human efforts in translation in an interactive-predictive platform. From our investigation we found that our syntax-aware interactive NMT (INMT) framework significantly reduces simulated human efforts in the French–to–English and Hindi–to–English translation tasks, achieving a 2.65 point absolute corresponding to 5.65% relative improvement and a 6.55 point absolute corresponding to 19.1% relative improvement, respectively, in terms of word prediction accuracy (WPA) over the respective baselines.
Keyword(s): Computational linguistics; Computer engineering; Machine learning; Machine translating
Publication Date:
2020
Type: Other
Peer-Reviewed: Unknown
Language(s): English
Institution: Dublin City University
Citation(s): Gupta, Kamal Kumar, Haque, Rejwanul ORCID: 0000-0003-1680-0099 <https://orcid.org/0000-0003-1680-0099>, Ekbal, Asif, Bhattacharyya, Pushpak and Way, Andy ORCID: 0000-0001-5736-5930 <https://orcid.org/0000-0001-5736-5930> (2020) Syntax-informed interactive neural machine translation. In: The International Joint Conference on Neural Networks (IJCNN), 19-24 July 2020, Glasgow, UK (Online). (In Press)
Publisher(s): IEEE
File Format(s): application/pdf
Related Link(s): http://doras.dcu.ie/24560/1/IJCNN_2020Syntax_Informed_Interactive_Neural_Machine_Translation.pdf,
https://2020.wcci-virtual.org/presentation/poster/syntax-informed-interactive-neural-machinetranslation
First Indexed: 2020-07-23 06:57:32 Last Updated: 2020-08-28 06:08:22