Online learning for effort reduction in interactive neural machine translation. (November 2019)

• Record Type: Journal Article
• Authors: Peris, Álvaro; Casacuberta, Francisco
• Is Part Of: Computer speech & language. Volume 58(2019)
• Page Start: 98
• Page End: 126
• Publication Date: 2019-11
• Subjects: Neural machine translation -- Interactive machine translation -- Machine translation post-editing -- Online learning -- Domain adaptation -- Deep learning; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2019.04.001
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: Application of online learning techniques to NMT post-editing and to interactive NMT. Novel method for for performing character-level interactions in interactive NMT. Experimentation conducted in three varied translation scenarios. Online learning and interactive machine translation bring significant improvements. Our adaptive, interactive systems outperform the existing state-of-the-art. We share all code developed in this work, in order to make research reproducible. Abstract: Neural machine translation systems require large amounts of training data and resources. Even with this, the quality of the translations may be insufficient for some users or domains. In such cases, the output of the system must be revised by a human agent. This can be done in a post-editing stage or following an interactive machine translation protocol. We explore the incremental update of neural machine translation systems during the post-editing or interactive translation processes. Such modifications aim to incorporate the new knowledge, from the edited sentences, into the translation system. Updates to the model are performed on-the-fly, as sentences are corrected, via online learning techniques. In addition, we implement a novel interactive, adaptive system, able to react to single-character interactions. This system greatly reduces the human effort required for obtaining high-quality translations. In order to stress our proposals, we conduct exhaustive experiments varying the amount and type of data available for training. Results show that online learning effectively achieves the objective of reducing the human effort required during the post-editing or the interactive machine translation stages. Moreover, these adaptive systems also perform well in scenarios with scarce resources. We show that a neural machine translation system can be rapidly adapted to a specific domain, exclusively by means of online learning techniques.