

#179 New Trends in Machine Translation with Large Language Models by Longyue Wang
Aug 18, 2023
Longyue Wang, a Research Scientist at Tencent AI Lab, discusses the advancements in Chinese-to-English machine translation and the challenges in translating Chinese to non-English languages. He explores the impact of large language models (LLMs) on machine translation, including their superiority in document-level translation. Longyue also highlights various promising research directions for LLMs in machine translation, such as stylized MT, interactive MT, and translation memory-based MT. Additionally, he sheds light on Chinese researchers' efforts to build Chinese-centric MT engines and reduce reliance on English as a pivot language.
Chapters
Transcript
Episode notes
1 2 3 4 5 6
Introduction
00:00 • 3min
Professional Background and Research in NLP and Machine Translation
03:07 • 3min
Machine Translation and Language Technology in Tencent
05:57 • 10min
Translation Challenges and Benefits of Large Language Models
16:21 • 14min
Language Technical Machine Translation in China, the US, and the European Union
30:35 • 3min
Future Plans for Large Language Models and Machine Translation
33:56 • 3min