ABSTRACT
The majority of inhabitants in Hong Kong are able to read and write in standard Chinese but use Cantonese as the primary spoken language in daily life. Spoken Cantonese can be transcribed into Chinese characters, which constitute the so-called written Cantonese. Written Cantonese exhibits significant lexical and grammatical differences from standard written Chinese. The rise of written Cantonese is increasingly evident in the cyber world. The growing interaction between Mandarin speakers and Cantonese speakers is leading to a clear demand for automatic translation between Chinese and Cantonese. This paper describes a transformer-based neural machine translation (NMT) system for written-Chinese-to-written-Cantonese translation. Given that parallel text data of Chinese and Cantonese are extremely scarce, a major focus of this study is on the effort of preparing good amount of training data for NMT. In addition to collecting 28K parallel sentences from previous linguistic studies and scattered internet resources, we devise an effective approach to obtaining 72K parallel sentences by automatically extracting pairs of semantically similar sentences from parallel articles on Chinese Wikipedia and Cantonese Wikipedia. We show that leveraging highly similar sentence pairs mined from Wikipedia improves translation performance in all test sets. Our system outperforms Baidu Fanyi's Chinese-to-Cantonese translation on 6 out of 8 test sets in BLEU scores. Translation examples reveal that our system is able to capture important linguistic transformations between standard Chinese and spoken Cantonese.
- Sutskever, I., Vinyals, O., and Le, Q. V. 2014. Sequence to sequence learning with neural networks. CoRR, abs/1409.3215.Google Scholar
- Gehring, J., Auli, M., Grangier, D., Yarats, D., and Dauphin, Y. N. 2017. Convolutional sequence to sequence learning. CoRR, abs/1705.03122.Google Scholar
- Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., and Polosukhin, I. 2017. Attention is all you need. CoRR, abs/1706.03762.Google Scholar
- Bahdanau, D., Cho, K., and Bengio, Y. 2015. Neural machine translation by jointly learning to align and translate. In 3rd International Conference on Learning Representations, San Diego, CA, USA.Google Scholar
- Snow, D. 2004. Cantonese as Written Language: The Growth of a Written Chinese Vernacular. Hong Kong University Press.Google Scholar
- Honnet, P. E., Popescu-Belis, A., Musat, C., and Baeriswyl, M. 2018. Machine translation of low-resource spoken dialects: Strategies for normalizing Swiss German. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan. European Language Resources Association (ELRA).Google Scholar
- Abe, K., Matsubayashi, Y., Okazaki, N., and Inui, K. 2018. Multi-dialect neural machine translation and dialectometry. In Proceedings of the 32nd Pacific Asia Conference on Language, Information and Computation, Hong Kong, 1–3 December. Association for Computational Linguistics.Google Scholar
- Artetxe, M. and Schwenk, H. 2018. Massively multilingual sentence embeddings for zero-shot cross-lingual transfer and beyond. CoRR, abs/1812.10464.Google Scholar
- Xu, P. and Fung, P. 2012. Cross-lingual language modeling with syntactic reordering for low-resource speech recognition. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 766-776, Jeju Island, Korea, July. Association for Computational Linguistics.Google Scholar
- Wong, T.-S. and Lee, J. 2018. Register-sensitive translation: a case study of Mandarin and Cantonese. In Proceedings of the 13th Conference of the Association for Machine Translation in the Americas (Volumn 1: Research Track), pages 89-96, Boston, MA, March. Association for Machine Translation in the Americas.Google Scholar
- Gibbons, J. 1987. Code-mixing and Code Choice: A Hong Kong Case Study. Multilingual Matters.Google Scholar
- Devlin, J., Chang, M. W., Lee, K., and Toutanova, K. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1, 4171-4186.Google Scholar
- Lee, J. 2011. Toward a parallel corpus of spoken Cantonese and written Chinese. In Proceedings of 5th International Joint Conference on Natural Language Processing, pages 1462-1466, Chiang Mai, Thailand, November. Asian Federation of Natural Language Processing.Google Scholar
- Wong, T.-S., Gerdes, K., Leung, H., and Lee, J. 2017. Quantitative comparative syntax on the Cantonese-Mandarin parallel dependency treebank. In Proceedings of the Fourth International Conference on Dependency Linguistics (Depling 2017), pages 266-275, Pisa, Italy, September, Linköping University Electronic Press.Google Scholar
- Schwenk, H., Chaudhary, V., Sun, S., Gong, H., and Guzmán, F. 2019. Wikimatrix: Mining 135m parallel sentences in 1620 language pairs from wikipedia. CoRR, abs/1907.05791.Google Scholar
- Papineni, K., Roukos, S., Ward, T., and Zhu, W. J. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pages 311–318, Philadelphia, Pennsylvania, USA, July. Association for Computational Linguistics.Google Scholar
Recommendations
Cantonese to Written Chinese Translation via HuggingFace Translation Pipeline
NLPIR '23: Proceedings of the 2023 7th International Conference on Natural Language Processing and Information RetrievalCantonese, a low-resource language [5] that has been used in Southeastern China for hundreds of years, with over 85 million native speakers worldwide, is poorly supported in the mainstream language model for existing translation platforms such as Baidu, ...
Low-resource automatic speech recognition and error analyses of oral cancer speech
AbstractIn this paper, we introduce a new corpus of oral cancer speech and present our study on the automatic recognition and analysis of oral cancer speech. A two-hour English oral cancer speech dataset is collected from YouTube. Formulated ...
Highlights- We introduce a new annotated dataset of oral cancer speech.
- We propose three ...
A Corpus-Based Analysis of Mixed Code in Hong Kong Speech
IALP '12: Proceedings of the 2012 International Conference on Asian Language ProcessingWe present a corpus-based analysis of the use of mixed code in Hong Kong speech. From transcriptions of Cantonese television programs, we identify English words embedded within Cantonese utterances, and investigate the motivations for such code-...
Comments