Yangjian Wu


2023

pdf bib
Exploring Prompt Engineering with GPT Language Models for Document-Level Machine Translation: Insights and Findings
Yangjian Wu | Gang Hu
Proceedings of the Eighth Conference on Machine Translation

This paper describes Lan-Bridge Translation systems for the WMT 2023 General Translation shared task. We participate in 2 directions: English to and from Chinese. With the emergence of large-scale models, various industries have undergone significant transformations, particularly in the realm of document-level machine translation. This has introduced a novel research paradigm that we have embraced in our participation in the WMT23 competition. Focusing on advancements in models such as GPT-3.5 and GPT-4, we have undertaken numerous prompt-based experiments. Our objective is to achieve optimal human evaluation results for document-level machine translation, resulting in our submission of the final outcomes in the general track.

pdf bib
UniBriVL: Robust Audio Representation and Generation of Audio Driven Diffusion Models
Sen Fang | Bowen Gao | Yangjian Wu | TeikToe Teoh
Proceedings of the 3rd Workshop on Multi-lingual Representation Learning (MRL)

2022

pdf bib
Lan-Bridge MT’s Participation in the WMT 2022 General Translation Shared Task
Bing Han | Yangjian Wu | Gang Hu | Qiulin Chen
Proceedings of the Seventh Conference on Machine Translation (WMT)

This paper describes Lan-Bridge Translation systems for the WMT 2022 General Translation shared task. We participate in 18 language directions: English to and from Czech, German, Ukrainian, Japanese, Russian, Chinese, English to Croatian, French to German, Yakut to and from Russian and Ukrainian to and from Czech.To develop systems covering all these direc_x0002_tions, we mainly focus on multilingual mod_x0002_els. In general, we apply data corpus filtering, scaling model size, sparse expert model (in par_x0002_ticular, Transformer with adapters), large scale backtranslation and language model rerankingtechniques. Our system ranks first in 6 directions based on automatic evaluation.