Using Sub-character Level Information for Neural Machine Translation of Logographic Languages

Zhang, Longtu; Komachi, Mamoru

doi:10.1145/3431727

Cited by 6 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…BPE denotes a subword based NMT with a joint vocabulary of 32K BPE tokens † † . Different to NMT for alphabetic languages, we can observe that the BPE approach in Japanese-Chinese NMT is inferior to the baseline using characters, which is consistent with the conclusions in [12], [13]. One reason is that the words in logographic languages are far shorter than words in alphabetic languages, which causes BPE failing to solve the low frequency words' problem.…”

Section: Resultssupporting

confidence: 76%

Sense-Aware Decoder for Character Based Japanese-Chinese NMT

LI,

REN

2024

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

Compared to subword based Neural Machine Translation (NMT), character based NMT eschews linguistic-motivated segmentation which performs directly on the raw character sequence, following a more absolute end-to-end manner. This property is more fascinating for machine translation (MT) between Japanese and Chinese, both of which use consecutive logographic characters without explicit word boundaries. However, there is still one disadvantage which should be addressed, that is, character is a less meaning-bearing unit than the subword, which requires the character models to be capable of sense discrimination. Specifically, there are two types of sense ambiguities existing in the source and target language, separately. With the former, it has been partially solved by the deep encoder and several existing works. But with the later, interestingly, the ambiguity in the target side is rarely discussed. To address this problem, we propose two simple yet effective methods, including a non-parametric pre-clustering for sense induction and a joint model to perform sense discrimination and NMT training simultaneously. Extensive experiments on Japanese↔Chinese MT show that our proposed methods consistently outperform the strong baselines, and verify the effectiveness of using sense-discriminated representation for character based NMT.

show abstract

Section: Resultssupporting

confidence: 76%

Sense-Aware Decoder for Character Based Japanese-Chinese NMT

LI,

REN

2024

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…On the other hand, language differences will also affect the political, economic, cultural, and military exchanges between countries. In recent years, the contacts between China and Japan have become more and more frequent and close, and doing a good job in Japanese translation has an important impact on the exchanges between the two countries [1][2][3][4].…”

Section: Introductionmentioning

confidence: 99%

Research on Improving the Quality of Japanese Chinese Machine Translation Based on Deep Learning

Lu,

Yin

2024

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

In order to improve the quality of Japanese-Chinese machine translation, the research on improving the quality of Japanese-Chinese machine translation based on deep learning is put forward. The maximum entropy model is used to effectively classify Japanese possible states and passive states, and then the features of Japanese possible states and passive states are effectively integrated into the log-linear model to improve the translation model, so as to improve the accuracy of selecting possible states and passive states in translation rules. The experimental results show that this method can effectively improve the translation quality of Japanese possible sentences and passive sentences. On large-scale Japanese Chinese materials, the maximum translation BLEU value can be increased from 41.50 to 42.01, and the overall intelligibility of translation results has been improved by 2.71% in manual evaluation. Conclusion: This method can improve the accuracy of rule selection.

show abstract

The boundaries of meaning: a case study in neural machine translation

Balashov

2022

Inquiry

View full text Add to dashboard Cite

The success of deep learning in natural language processing raises intriguing questions about the nature of linguistic meaning and ways in which it can be processed by natural and artificial systems. One such question has to do with subword segmentation algorithms widely employed in language modeling, machine translation, and other tasks since 2016. These algorithms often cut words into semantically opaque pieces, such as 'period', 'on', 't', and 'ist' in 'period|on|t|ist'. The system then represents the resulting segments in a dense vector space, which is expected to model grammatical relations among them. This representation may in turn be used to map 'period|on|t|ist' (English) to 'par|od|ont|iste' (French). Thus, instead of being modeled at the lexical level, translation is reformulated more generally as the task of learning the best bilingual mapping between the sequences of subword segments of two languages; and sometimes even between pure character sequences: 'p|e|r|i|o|d|o|n|t|i|s|t|' → 'p|a|r|o|d|o|n|t|i|s|t|e'. Such subword segmentations and alignments are at work in highly efficient end-to-end machine translation systems, despite their allegedly opaque nature. The computational value of such processes is unquestionable. But do they have any linguistic or philosophical plausibility? I attempt to cast light on this question by reviewing the relevant details of the subword segmentation algorithms and by relating them to important philosophical and linguistic debates, in the spirit of making artificial intelligence more transparent and explainable.

show abstract

Using Sub-character Level Information for Neural Machine Translation of Logographic Languages

Cited by 6 publications

References 15 publications

Sense-Aware Decoder for Character Based Japanese-Chinese NMT

Sense-Aware Decoder for Character Based Japanese-Chinese NMT

Research on Improving the Quality of Japanese Chinese Machine Translation Based on Deep Learning

The boundaries of meaning: a case study in neural machine translation

Contact Info

Product

Resources

About