Abstract
The translation quality of Neural Machine Translation (NMT) systems depends strongly on the training data size. Sufficient amounts of parallel data are, however, not available for many language pairs. This paper presents a corpus augmentation method, which has two variations: one is for all language pairs, and the other is for the Chinese-Japanese language pair. The method uses both source and target sentences of the existing parallel corpus and generates multiple pseudo-parallel sentence pairs from a long parallel sentence pair containing punctuation marks as follows: (1) split the sentence pair into parallel partial sentences; (2) back-translate the target partial sentences; and (3) replace each partial sentence in the source sentence with the back-translated target partial sentence to generate pseudo-source sentences. The word alignment information, which is used to determine the split points, is modified with “shared Chinese character rates” in segments of the sentence pairs. The experiment results of the Japanese-Chinese and Chinese-Japanese translation with ASPEC-JC (Asian Scientific Paper Excerpt Corpus, Japanese-Chinese) show that the method substantially improves translation performance. We also supply the code (see Supplementary Materials) that can reproduce our proposed method.
Highlights
In recent years, Neural Machine Translation (NMT) has made remarkable achievements [1]
Zero-shot translation is a translation mechanism that uses a single NMT engine to translate between multiple languages, even such low-resource languages for which no direct parallel data were provided during training
We propose a method to augment a parallel corpus by sentence segmentation and synthesis
Summary
Neural Machine Translation (NMT) has made remarkable achievements [1]. Zero-shot translation is a translation mechanism that uses a single NMT engine to translate between multiple languages, even such low-resource languages for which no direct parallel data were provided during training. Expanding the size of the training data (parallel corpus) is an effective way to improve the translation performance for NMT in low-resource language pairs. We show that we can improve the NMT system’s translation performance by mixing generated pseudo-parallel sentence pairs into training data with no monolingual data and without changing the neural network architecture. This process makes our approach applicable to different NMT architectures.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
