no code implementations • NAACL (maiworkshop) 2021 • Han Ding, Li Erran Li, Zhiting Hu, Yi Xu, Dilek Hakkani-Tur, Zheng Du, Belinda Zeng
Recent vision-language understanding approaches adopt a multi-modal transformer pre-training and finetuning paradigm.
no code implementations • ECNLP (ACL) 2022 • Bo Dong, Yiyi Wang, Hanbo Sun, Yunji Wang, Alireza Hashemi, Zheng Du
In this paper, we propose a contrastive meta-learning framework (CML) to address the challenges introduced by noisy annotated data, specifically in the context of natural language processing.
no code implementations • 13 Dec 2023 • Jiang Zhang, Qiong Wu, Yiming Xu, Cheng Cao, Zheng Du, Konstantinos Psounis
Furthermore, student LMs fine-tuned with rationales extracted via DToT outperform baselines on all datasets with up to 16. 9\% accuracy improvement, while being more than 60x smaller than conventional LLMs.
1 code implementation • 24 Sep 2023 • Jian Gao, Hanbo Sun, Cheng Cao, Zheng Du
We collect and release LibriCrowd - a large-scale crowdsourced dataset of audio transcriptions on 100 hours of English speech.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 18 Sep 2023 • Hanbo Sun, Jian Gao, Xiaomin Wu, Anjie Fang, Cheng Cao, Zheng Du
Therefore, we propose HTEC for Human Transcription Error Correction.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 6 Feb 2023 • Sunyi Chi, Bo Dong, Yiming Xu, Zhenyu Shi, Zheng Du
Lastly, our sensitive analysis emphasizes the capability of the proposed framework to handle the long-tailed problem and mitigate the negative impact of noisy labels.