1 code implementation • 28 Feb 2024 • Yuan Ge, Yilun Liu, Chi Hu, Weibin Meng, Shimin Tao, Xiaofeng Zhao, Hongxia Ma, Li Zhang, Hao Yang, Tong Xiao
The second step involves preserving dataset diversity through a clustering process. In our experiment, CaR selected a subset containing only 1. 96% of Alpaca's IT data, yet the underlying AlpaCaR model trained on this subset outperforms Alpaca by an average of 32. 1% in GPT-4 evaluations.
no code implementations • 21 Jan 2024 • Yuang Li, Jiawei Yu, Yanqing Zhao, Min Zhang, Mengxin Ren, Xiaofeng Zhao, Xiaosong Qiao, Chang Su, Miaomiao Ma, Hao Yang
In this work, we connect the Whisper encoder with ChatGLM3 and provide in-depth comparisons of these two approaches using Chinese automatic speech recognition (ASR) and name entity recognition (NER) tasks.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
2 code implementations • 22 Nov 2023 • Yilun Liu, Shimin Tao, Xiaofeng Zhao, Ming Zhu, Wenbing Ma, Junhao Zhu, Chang Su, Yutai Hou, Miao Zhang, Min Zhang, Hongxia Ma, Li Zhang, Hao Yang, Yanfei Jiang
Instruction tuning is crucial for enabling Language Learning Models (LLMs) in responding to human instructions.
no code implementations • 18 Sep 2023 • Yuang Li, Yinglu Li, Min Zhang, Chang Su, Mengxin Ren, Xiaosong Qiao, Xiaofeng Zhao, Mengyao Piao, Jiawei Yu, Xinglin Lv, Miaomiao Ma, Yanqing Zhao, Hao Yang
End-to-end automatic speech recognition (ASR) systems often struggle to recognize rare name entities, such as personal names, organizations, and terminologies not frequently encountered in the training data.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
1 code implementation • 9 Dec 2021 • Feiliang Ren, Longhui Zhang, Xiaofeng Zhao, Shujuan Yin, Shilei Liu, Bochao Li
Moreover, experiments show that both the proposed bidirectional extraction framework and the share-aware learning mechanism have good adaptability and can be used to improve the performance of other tagging based methods.
no code implementations • 4 Nov 2021 • Mingao Yuan, Bin Zhao, Xiaofeng Zhao
In practice, a network may has censored (or missing) values and it is shown that censored values have non-negligible effect on the structural properties of a network.
1 code implementation • EMNLP 2021 • Feiliang Ren, Longhui Zhang, Shujuan Yin, Xiaofeng Zhao, Shilei Liu, Bochao Li, Yaduo Liu
Next, the mined global associations are integrated into the table feature of each relation.
1 code implementation • EMNLP 2021 • Shilei Liu, Xiaofeng Zhao, Bochao Li, Feiliang Ren, Longhui Zhang, Shujuan Yin
Neural conversation models have shown great potentials towards generating fluent and informative responses by introducing external background knowledge.
no code implementations • 31 Aug 2021 • Shilei Liu, Xiaofeng Zhao, Bochao Li, Feiliang Ren
Knowledge-grounded dialogue is a task of generating a fluent and informative response based on both conversation context and a collection of external knowledge, in which knowledge selection plays an important role and attracts more and more research interest.
1 code implementation • 20 Aug 2021 • Feiliang Ren, Longhui Zhang, Shujuan Yin, Xiaofeng Zhao, Shilei Liu, Bochao Li
Tagging based methods are one of the mainstream methods in relational triple extraction.
1 code implementation • 16 Aug 2021 • Yaduo Liu, Longhui Zhang, Shujuan Yin, Xiaofeng Zhao, Feiliang Ren
Finally, our system ranks No. 4 on the test set leader-board of this multi-format information extraction task, and its F1 scores for the subtasks of relation extraction, event extractions of sentence-level and document-level are 79. 887%, 85. 179%, and 70. 828% respectively.