no code implementations • 28 Jan 2024 • Jianqiao Lu, Wanjun Zhong, YuFei Wang, Zhijiang Guo, Qi Zhu, Wenyong Huang, Yanlin Wang, Fei Mi, Baojun Wang, Yasheng Wang, Lifeng Shang, Xin Jiang, Qun Liu
With the teacher's guidance, the student learns to iteratively refine its answer with feedback, and forms a robust and comprehensive understanding of the posed questions.
no code implementations • 16 Oct 2023 • Kai Chen, Chunwei Wang, Kuo Yang, Jianhua Han, Lanqing Hong, Fei Mi, Hang Xu, Zhengying Liu, Wenyong Huang, Zhenguo Li, Dit-yan Yeung, Lifeng Shang, Xin Jiang, Qun Liu
The rapid development of large language models (LLMs) has not only provided numerous opportunities but also presented significant challenges.
no code implementations • 9 Oct 2023 • Jianqiao Lu, Wenyong Huang, Nianzu Zheng, Xingshan Zeng, Yu Ting Yeung, Xiao Chen
For SLU, LaSyn improves our E2E baseline by absolute 4. 1% for intent classification accuracy and 3. 8% for slot filling SLU-F1 on SLURP, and absolute 4. 49% and 2. 25% for exact match (EM) and EM-Tree accuracies on STOP respectively.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +6
no code implementations • 1 Oct 2023 • Jianqiao Lu, Wanjun Zhong, Wenyong Huang, YuFei Wang, Qi Zhu, Fei Mi, Baojun Wang, Weichao Wang, Xingshan Zeng, Lifeng Shang, Xin Jiang, Qun Liu
SELF initiates with a meta-skill learning process that equips the LLMs with capabilities for self-feedback and self-refinement.
1 code implementation • 24 Jul 2023 • YuFei Wang, Wanjun Zhong, Liangyou Li, Fei Mi, Xingshan Zeng, Wenyong Huang, Lifeng Shang, Xin Jiang, Qun Liu
(2) Training methodologies: a detailed review of the prevailing training methods employed for LLM alignment.
1 code implementation • ICLR 2022 • Wenyong Huang, Zhenhe Zhang, Yu Ting Yeung, Xin Jiang, Qun Liu
The student network is trained to output representation resembling that of the teacher.
no code implementations • 16 Nov 2021 • Nianzu Zheng, Liqun Deng, Wenyong Huang, Yu Ting Yeung, Baohua Xu, Yuanyuan Guo, Yasheng Wang, Xiao Chen, Xin Jiang, Qun Liu
We utilize conv-transformer structure to encode input speech in a streaming manner.
no code implementations • 13 Aug 2020 • Wenyong Huang, Wenchao Hu, Yu Ting Yeung, Xiao Chen
To reduce computation cost, we gradually downsample acoustic input, also with the interleaved convolution layers.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
10 code implementations • 31 Aug 2019 • Junqiu Wei, Xiaozhe Ren, Xiaoguang Li, Wenyong Huang, Yi Liao, Yasheng Wang, Jiashu Lin, Xin Jiang, Xiao Chen, Qun Liu
The pre-trained language models have achieved great successes in various natural language understanding (NLU) tasks due to its capacity to capture the deep contextualized information in text by pre-training on large-scale corpora.