Improving character-level Japanese-Chinese neural machine translation with radicals as an additional input feature

Abstract

In recent years, Neural Machine Translation (NMT) has been proven to get impressive results. While some additional linguistic features of input words improve wordlevel NMT, any additional character features have not been used to improve character-level NMT so far. In this paper, we show that the radicals of Chinese characters (or kanji), as a character feature information, can be easily provide further improvements in the character-level NMT. In experiments on WAT2016 Japanese-Chinese scientific paper excerpt corpus (ASPEC-JP), we find that the proposed method improves the translation quality according to two aspects: perplexity and BLEU. The character-level NMT with the radical input feature's model got a state-of-the-art result of 40.61 BLEU points in the test set, which is an improvement of about 8.6 BLEU points over the best system on the WAT2016 Japaneseto-Chinese translation subtask with ASPEC-JP. The improvements over the character-level NMT with no additional input feature are up to about 1.5 and 1.4 BLEU points in the development-test set and the test set of the corpus, respectively.

WCC-JC: A Web-Crawled Corpus for Japanese-Chinese Neural Machine Translation

“…For Japanese-Chinese translation, Zhang et al proposed the following three data augmentation methods to improve the quality of Japanese-Chinese NMT: (1) radicals as an additional input feature [25]; (2) the created Chinese character decomposition table [26]; (3) a corpus augmentation approach [27], considering the lack of resources in bilingual corpora.…”

“…Corpus linguistics [3] Japanese-Chinese bilingual corpora [1], TED talks, [4,5] Web-crawled corpora [7][8][9][10][11]13,14,16,17,19,24] Other corpora [6,12,18,[20][21][22] Corpus augmentation [15,23,[25][26][27] The above related research showed that corpora play an important role in improving translation accuracy and in other directions of language processing. Thus, the construction of a Japanese-Chinese bilingual corpus for NMT has significant implications for the resource scarcity problem.…”

Robust Neural Machine Translation with ASR Errors

“…Our approach is motivated by the work of NMT incorporated with linguistic input features . Chinese linguistic features, such as radicals and Pinyin, have been demonstrated effective to Chinese-sourced NMT (Liu et al, 2019;Zhang and Matsumoto, 2017;Du and Way, 2017) and Chinese ASR (Chan and Lane, 2016). We also incorporate Pinyin as an additional input feature in the robust NMT model, aiming at improving the robustness of NMT further.…”

Proceedings of the First Workshop on Automatic Simultaneous Translation

“…Our approach is motivated by the work of NMT incorporated with linguistic input features . Chinese linguistic features, such as radicals and Pinyin, have been demonstrated effective to Chinese-sourced NMT Zhang and Matsumoto, 2017;Du and Way, 2017) and Chinese ASR (Chan and Lane, 2016). We also incorporate Pinyin as an additional input feature in the robust NMT model, aiming at improving the robustness of NMT further.…”