SlatorPod

#179 New Trends in Machine Translation with Large Language Models by Longyue Wang

August 18, 2023 Slator
SlatorPod
#179 New Trends in Machine Translation with Large Language Models by Longyue Wang
Show Notes Chapter Markers

Joining SlatorPod this week is Longyue Wang, a Research Scientist at Tencent AI Lab, where he is involved in the research and practical applications of machine translation (MT) and natural language processing (NLP).

Longyue Longyue expands on Tencent’s approach to language technology where they integrate MT with Tencent Translate (TranSmart). He highlights how Chinese-to-English MT has made significant advancements, thanks to improvements in technology and data size. However, translating Chinese to non-English languages has been more challenging.

Recent research by Longyue explores large language models’ (LLMs) impact on MT, demonstrating their superiority in tasks like document-level translation. He emphasized that GPT-4 outperformed traditional MT engines in translating literary texts like web novels.

Longyue discusses various promising research directions for MT using LLMs, including stylized MT, interactive MT, translation memory-based MT, and a new evaluation paradigm. His research suggests LLMs can enhance personalized MT, adapting translations to users' preferences.

Longyue also sheds light on how Chinese researchers are focusing on building Chinese-centric MT engines, directly translating from Chinese to other languages. There's an effort to reduce reliance on English as a pivot language.

Looking ahead, Longyue's research will address challenges related to LLMs, including handling hallucination and timeless information issues.

Intro
What is Tencent?
Professional Background and Interest in MT and NLP
Tencent's Interest in Language Technology
Perception of Language Technology in China
MT Quality for Chinese
ChatGPT's Translation Capabilities
Interesting Directions for MT Using LLMs
Translation Memory-Based MT
Interactive MT
Using ChatGPT to Evaluate Translation
Personalized MT and Multi-Modal MT
The Focus of China-Based Research
Future Research Initiatives