Online learning for effort reduction in interactive neural machine translation

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.3. We conduct a large experimentation, using public corpora containing different features from varied domains. We stress the translation systems, applying them in three different translation scenarios. 4. We show that OL brings significant improvements to the translation engines, in terms of translation quality and human effort reduction. Comparisons with other works in the literature also show that our adaptive, interactive systems are able to outperform the existing state-of-the-art. 5. We open-source all code developed in this work, in order to make research reproducible.The rest of this manuscript is structured as follows: the related work is reviewed in Section 2. Next, Section 3 briefly introduces the NMT technology, while the interactive protocol for NMT is presented in Section 4. OL is described and applied together with INMT in Section 5. Section 6 describes the experimental setup of this work. Results are presented and discussed in Section 7. Finally, we conclude the work and trace future lines of work in Section 8. Related workThis work puts together three thoroughly studied fields: neural machine translation, interactive machine translation and online learning. In this section, we briefly review the progress made in the last years in each one of these fields. Neural machine translationAlthough the first attempts of performing machine translation with neural networks date from long ago (Castaño and Casacuberta, 1997; Forcada andÑeco, 1997), NMT only took off recently. Kalchbrenner and Blunsom (2013) reintroduced full neural MT, although the results were non-competitive with re...

NMT-Keras: a Very Flexible Toolkit with a Focus on Interactive NMT and Online Learning

“…Due to space restrictions, we report results on two tasks: EU (Barrachina et al, 2009) and Europarl (Koehn, 2005). More extensive results obtained with NMT-Keras can be found at Peris and Casacuberta (2018a). For the first task, we used the standard partitions.…”

“…Ortiz-Martínez, 2016). The NMT system was configured as in Peris and Casacuberta (2018a). For the sake of comparison, we include results of phrase-based statistical machine translation (PB-SMT), using the standard setup of Moses (Koehn et al, 2007).…”

“…NMT-Keras implements the interactive protocols described by Peris et al (2017c). Moreover, they can be combined with online learning (OL) or active learning methods, which allow to specialize the system into a given domain or to the preferences of a user (Peris and Casacuberta, 2018a). These protocols are also implemented in NMT-Keras.…”

“…† refers to Ortiz-Martínez (2016), ‡ to Barrachina et al (2009). Extended results can be found in Peris and Casacuberta (2018a). Table 2 shows the performance in KSMR (%) of the INMT systems.…”

A Neural, Interactive-predictive System for Multimodal Sequence to Sequence Tasks

“…Then, it is validated. As soon as the sentence is validated, the system can be incrementally updated with this sample, following an online learning setup (Peris and Casacuberta, 2019). Hence, in future interactions, the system will be progressively updated, tailoring to a given domain or to the user preferences.…”