ᴲ㷞ഊ • FOCAL STORY 澳大ᑓゆ • 2019 UMAGAZINE 20 13 with researchers from Tsinghua. ‘The biggest gain for me was that we thoroughly studied and mastered the architecture,’ he says. In November 2018, the team returned to Macao and began to gradually integrate the latest technologies in UM-CAT to improve the system’s ability for deep learning. Dr Liu explains: ‘In the past, training machine translation systems relied heavily on parallel corpora. We are talking about millions of Chinese texts and corresponding Portuguese translations. But now, we constantly update the parameters of each neuron in the neural network. In other words, each time we develop a better neural network, the quality of the translation will greatly improve as a consequence, either by reducing the occurrence of overlooked words, or by improving the readability of the translation.’ The team in the NLP2CT and their counterparts from Tsinghua University have submitted two jointly authored papers to international journals. A patent is also pending for approval. ⅰᙉᗖ䢬Ǘᕍ大ⅰᏹൄ ᒴᇮ㐛個ᙉ ᗖ⚋研㐓̜ ǎǘ 201 11ᕓ䢬研॰㡴ो澳㟑䢬˧ 㟘ୣ ⮍ᆼᇮᕍᑓⅰᇤ⻐㐔ଊ6. $"5☲⚕˔䢬͞ ࠴Ր࣮ ᪦ༀಾ⠗ ⅰ能؛ǎ،ಾ ژ ゐ䢺Ǘ͞ נ 䢬࣮ 翻 譯☲⚕ⅰ〠⛿䢬ϭㇹᑜ大⿈ឹ ⅰ平⻋ ゆᑁ༄䢬 ګ ᒴⅬ⭤۴中ᐵ譯ᕲ䢬⦾ Ր⇀ഭᅞⅰ葡ᐵ譯ᐵ䢬έॺᒴ˗ᑘᕅ ᑓ⎖⚭⛆㊊中ᣵˍ⎖⚭Ԫⅰۜ ᐨǎየ 〓́ 䢬۸⾾〲〘֦ ᕅତⅰ⎖⚭⛆㊊䢬 㒄㷃翻譯ㇰ㕵̏ ᕐ⇀ᅞঁ 㧧⮍ዞ㭗䢬 ۽ ᪾റᮆತⅰႌᦵ䢬ᆖ譯ᐵゆ۴ㅊྲ ᕅ؝ᨢᔊǎǘ↷ נ 䢬澳大/-12$5॰ 㡴ᕔՇ╊⦾᪷ ⬷⮍ⅰಾ⻐グᐵᢩ ܗ २㢂ಾ⻐ᕧֳ ᇷ中䢬㑮ᕔˍ㦕നᢩྦ ഔᇝ中ǎ /-12$5ಢ⢺⇶૦࣮ 翻譯̿ ᆾ The NLP2CT has nurtured many machine translation researchers over the years
RkJQdWJsaXNoZXIy MTQ1NDU2Ng==