2 code implementations • 8 Apr 2024 • Longhui Zhang, Dingkun Long, Meishan Zhang, Yanzhao Zhang, Pengjun Xie, Min Zhang
Experimental results on Chinese sequence labeling datasets demonstrate that the improved BABERT variant outperforms the vanilla version, not only on these tasks but also more broadly across a range of Chinese natural language understanding tasks.
1 code implementation • 28 Nov 2023 • Longhui Zhang, Yanzhao Zhang, Dingkun Long, Pengjun Xie, Meishan Zhang, Min Zhang
In this work, we propose a two-stage progressive paradigm to better adapt LLMs to text ranking.
no code implementations • 23 Aug 2023 • Guangwei Xu, Yangzhao Zhang, Longhui Zhang, Dingkun Long, Pengjun Xie, Ruijie Guo
Large-scale text retrieval technology has been widely used in various practical business scenarios.
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.
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.
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.