The University of Macau (UM) has achieved yet another breakthrough\nin machine translation! A research team from UM recently developed a new system\nfor translation between Cantonese and Mandarin. The system can efficiently and accurately\ntranslate text between the two dialects. Already available on the internet, the\ntranslation system is significant for the integration and development of the\neconomic, cultural, and tourism industries in the Guangdong-Hong Kong-Macao\nGreater Bay Area.<\/p>\n\n
The Cantonese-Mandarin translation system was developed by UM\u2019s\nNatural Language Processing & Portuguese \u2013 Chinese Machine Translation\nLaboratory (NLP2<\/sup>CT).\nAs a response to China\u2019s national development strategies, examples of which\ninclude the Belt and Road Initiative and the Greater Bay Area, the lab initiated\na research study titled \u2018Unsupervised Neural Dialect\nTranslation with Commonality and Diversity Modeling\u2019 by utilising Macao\u2019s\nunique economic and cultural advantages. The related paper was accepted at the\nAssociation for the Advancement of Artificial Intelligence (AAAI) Conference on\nArtificial Intelligence 2020, a top international conference in the field. This\nyear\u2019s event received a record number of papers (8,800), and only 1,591 were accepted.\nThe Cantonese-Mandarin translation system is now available on the internet. Currently,\nthe UM research team is developing\na machine translation system and a simultaneous interpretation system between\nCantonese and Portuguese, which will use the world\u2019s latest technologies to improve\ntrilingual machine translation among Chinese, Portuguese, and English. They will\nrepresent new breakthroughs after the UM-CAT, an online\nChinese-Portuguese-English computer-aided translation platform.<\/p>\n\n Cantonese-Mandarin translation belongs to the category of dialect\ntranslation. Although the two dialects bear some similarities, there are differences\nin syntax. With a significant lack of parallel data between the two dialects,\nit is difficult to develop an ideal translation model based on current machine\ntranslation methods. For this reason, the research group from UM proposed a\nnovel Unsupervised Neural Machine Translation (UNMT) model by introducing\nPivot-Private embeddings and coordinating the learning of word representations\nfrom both the encoder and decoder in a layer-wise approach, to model the\ncommonalities and diversities of Cantonese and Mandarin at different levels\n(morphology, syntax, and semantics). The model achieved state-of-the-art\nCantonese-Mandarin translation performance only by using monolingual<\/i>\ndata, significantly outperforming the rule-based approaches and the existing\nunsupervised NMT models. This\napproach can greatly enhance translation quality and both machine\nself-evaluation and human evaluation have confirmed the new approach\u2019s high degree\nof efficiency and accuracy.<\/p>\n\n The\nmultidisciplinary team at the lab has won numerous awards for their\nachievements, including a second prize at the Macao Science and Technology\nAwards in the Science and Technology Progress Award category for their project\nthat studied the technologies related to Chinese\/Portuguese machine translation\nsystems and the applications of the systems. The neural-based machine translation\nsystems developed by the lab won several prizes at the constraint\nEnglish-to-Chinese machine translation campaign organised under the 13th<\/sup> China\nWorkshop on Machine Translation (CWMT 2017). In the future, the lab hopes to achieve\nnew breakthroughs in the area of machine translation in order to remove\nlanguage barriers between Guangdong, Hong Kong, Macao, and Portugal, and to fulfill\nthe need for ever-increasing cultural exchange between Macao, the Greater Bay\nArea, and Portuguese-speaking countries.<\/p> <\/p> Source: Faculty of Science and Technology <\/p> Media Contact Information: Communications Office, University of Macau<\/p> <\/p> <\/p> <\/p> <\/p> <\/p> <\/p> <\/p> <\/p> <\/p> <\/p> <\/p> <\/p> Albee Lei Tel\uff1a(853) 88228004Kelvin U Tel\uff1a(853) 88224322Email\uff1aprs.media@um.edu.moUM Website\uff1awww.um.edu.mo<\/p> <\/p>\n \n ","protected":false},"excerpt":{"rendered":" The University of Macau (UM) has achieved yet another breakthrough in machine translation! A research team from UM recently developed a new system for translation between Cantonese and Mandarin. The…<\/p>\n","protected":false},"author":1,"featured_media":21166,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[60],"tags":[],"class_list":["post-21165","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-press-release"],"acf":[],"yoast_head":"\n