Multi-Source Neural Machine Translation with Data Augmentation

By Yuta Nishimura, Katsuhito Sudoh, Graham Neubig, Satoshi Nakamura. 2018

22 citations recorded by the source corpus.

Multi-source translation systems translate from multiple languages to a single target language. By using information from these multiple sources, these systems achieve large gains in accuracy. To train these systems, it is necessary to have corpora with parallel text in multiple sources and the target language. However, these corpora are rarely complete in practice due to the difficulty of providing human translations in all of the relevant languages. In this paper, we propose a data augmentation approach to fill such incomplete parts using multi-source neural machine translation (NMT). In our experiments, results varied over different language combinations but significant gains were observed when using a source language similar to the target language.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

A Survey of Data Augmentation Approaches for NLP (2021, methodology): “Nishimura et al. (2018) Introduce DA methods for multi-source NMT that ﬁlls in incomplete portions of multi-source training data.”
Neural Machine Translation for Low-resource Languages: A Survey (2021, background): “This restriction can be relaxed by either marking a corresponding sentence as null if a particular language does not have that sentence [142] or by generating the missing sentences with a pre-trained model [141].”
Generalized Data Augmentation for Low-Resource Translation (2019, background): “More related with data augmentation, Nishimura et al. (2018) ﬁll in missing data with a multi-source setting to boost multilingual translation.”
Multi-Source Transformer for Kazakh-Russian-English Neural Machine Translation (2019, methodology): “…to attend to both the original sentence and its translation using multi-source techniques (Zoph and Knight, 2016; Libovick´y and Helcl, 2017; Nishimura et al., 2018); we hypothesized that giving the system both the originals and “cross-translations”, in both directions (Kazakh-to-Russian…”
A Survey of Multilingual Neural Machine Translation (2019, background): “[108] extended Reference [168] by representing each “missing” source language with a dummy token.”
Multi-Source Neural Machine Translation with Missing Data (2018, background): “1This journal article is based on content previously presented as two workshop proceedings [13], [14].”
Neural Machine Translation: A Review (2019, unknown): “A problem with this approach is data sparsity as missing source sentences have to be synthesized (Choi et al., 2018a; Nishimura et al., 2018) if the training corpus does not”