Junwei Liao

According to our database, Junwei Liao authored at least 9 papers between 2021 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Pretraining without wordpieces: learning over a vocabulary of millions of words.

Zhangyin Feng, Duyu Tang, Xiaocheng Feng, Cong Zhou, Junwei Liao, Shuangzhi Wu, Bing Qin, Yunbo Cao, Shuming Shi

Int. J. Mach. Learn. Cybern., September, 2024

Agentic Information Retrieval.

Weinan Zhang, Junwei Liao, Ning Li, Kounianhua Du

CoRR, 2024

Hammer: Robust Function-Calling for On-Device Language Models via Function Masking.

Qiqiang Lin, Muning Wen, Qiuying Peng, Guanyu Nie, Junwei Liao, Jun Wang, Xiaoyun Mo, Jiamu Zhou, Cheng Cheng, Yin Zhao, Weinan Zhang

CoRR, 2024

2023

Text Polishing with Chinese Idiom: Task, Datasets and Pre-trained Baselines.

Junwei Liao, Shuai Cheng, Minghuan Tan

ACM Trans. Asian Low Resour. Lang. Inf. Process., June, 2023

Improving Readability for Automatic Speech Recognition Transcription.

Junwei Liao, Sefik Emre Eskimez, Liyang Lu, Yu Shi, Ming Gong, Linjun Shou, Hong Qu, Michael Zeng

ACM Trans. Asian Low Resour. Lang. Inf. Process., May, 2023

Skillnet-NLG: General-Purpose Natural Language Generation with a Sparsely Activated Approach.

Junwei Liao, Duyu Tang, Fan Zhang, Shuming Shi

Proceedings of the IEEE International Conference on Acoustics, 2023

2022

Automatic Speech Recognition Post-Processing for Readability: Task, Dataset and a Two-Stage Pre-Trained Approach.

Junwei Liao, Yu Shi, Yong Xu

IEEE Access, 2022

2021

Improving Zero-shot Neural Machine Translation on Language-specific Encoders- Decoders.

Junwei Liao, Yu Shi, Ming Gong, Linjun Shou, Hong Qu, Michael Zeng

Proceedings of the International Joint Conference on Neural Networks, 2021

Generating Human Readable Transcript for Automatic Speech Recognition with Pre-Trained Language Model.

Junwei Liao, Yu Shi, Ming Gong, Linjun Shou, Sefik Emre Eskimez, Liyang Lu, Hong Qu, Michael Zeng

Proceedings of the IEEE International Conference on Acoustics, 2021