Search Results for author: Jinliang Lu

Found 4 papers, 3 papers with code

BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing

1 code implementation2 Sep 2023 Chen Wang, Minpeng Liao, Zhongqiang Huang, Jinliang Lu, Junhong Wu, Yuchen Liu, Chengqing Zong, Jiajun Zhang

One is a cascaded approach where outputs (tokens or states) of a separately trained speech recognition system are used as inputs for LLMs, which limits their potential in modeling alignment between speech and text.

speech-recognition Speech Recognition +1

Instance-aware Prompt Learning for Language Understanding and Generation

1 code implementation18 Jan 2022 Feihu Jin, Jinliang Lu, Jiajun Zhang, Chengqing Zong

Specifically, we suppose that each learnable prompt token has a different contribution to different instances, and we learn the contribution by calculating the relevance score between an instance and each prompt token.

Few-Shot Learning

Exploiting Curriculum Learning in Unsupervised Neural Machine Translation

1 code implementation Findings (EMNLP) 2021 Jinliang Lu, Jiajun Zhang

Back-translation (BT) has become one of the de facto components in unsupervised neural machine translation (UNMT), and it explicitly makes UNMT have translation ability.

Machine Translation Translation

Cannot find the paper you are looking for? You can Submit a new open access paper.