no code implementations • Findings (EMNLP) 2021 • Tongliang Li, Lei Fang, Jian-Guang Lou, Zhoujun Li
In this paper, we propose to generate text conditioned on the structured data (table) and a prefix (the written text) by leveraging the pre-trained models.
no code implementations • 13 Apr 2024 • Shun Zhang, Chaoran Yan, Jian Yang, Changyu Ren, Jiaqi Bai, Tongliang Li, Zhoujun Li
To address the aforementioned challenges, we propose a Robust New Intent Discovery (RoNID) framework optimized by an EM-style method, which focuses on constructing reliable pseudo-labels and obtaining cluster-friendly discriminative representations.
no code implementations • 25 Mar 2024 • Shun Zhang, Jian Yang, Jiaqi Bai, Chaoran Yan, Tongliang Li, Zhao Yan, Zhoujun Li
New Intent Discovery (NID) aims to recognize known and infer new intent categories with the help of limited labeled and large-scale unlabeled data.
1 code implementation • 18 Jan 2024 • Xianfu Cheng, Weixiao Zhou, Xiang Li, Xiaoming Chen, Jian Yang, Tongliang Li, Zhoujun Li
In this work, we propose the VIsion Permutable extractor for fast and efficient scene Text Recognition (VIPTR), which achieves an impressive balance between high performance and rapid inference speeds in the domain of STR.
no code implementations • 13 Jan 2024 • Linzheng Chai, Jian Yang, Tao Sun, Hongcheng Guo, Jiaheng Liu, Bing Wang, Xiannian Liang, Jiaqi Bai, Tongliang Li, Qiyao Peng, Zhoujun Li
To bridge the gap among different languages, we propose a cross-lingual instruction fine-tuning framework (xCOT) to transfer knowledge from high-resource languages to low-resource languages.
no code implementations • 15 Sep 2023 • Xianjie Wu, Jian Yang, Tongliang Li, Di Liang, Shiwei Zhang, Yiyang Du, Zhoujun Li
To fully Unleash the potential of evidence, we propose a framework to effectively incorporate Evidence in knowledge-Intensive Dialogue Generation (u-EIDG).
2 code implementations • 12 Aug 2023 • Tongliang Li, Zixiang Wang, Linzheng Chai, Jian Yang, Jiaqi Bai, Yuwei Yin, Jiaheng Liu, Hongcheng Guo, Liqun Yang, Hebboul Zine el-abidine, Zhoujun Li
Cross-lingual open information extraction aims to extract structured information from raw text across multiple languages.
no code implementations • 11 Jan 2023 • Zixiang Wang, Jian Yang, Tongliang Li, Jiaheng Liu, Ying Mo, Jiaqi Bai, Longtao He, Zhoujun Li
In this paper, we propose a two-stage multilingual training method and a joint model called Multilingual Entity and Relation Extraction framework (mERE) to mitigate language interference across languages.