Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Huang, Shijue"'
Autor:
Qin, Libo, Wei, Fuxuan, Chen, Qiguang, Zhou, Jingxuan, Huang, Shijue, Si, Jiasheng, Lu, Wenpeng, Che, Wanxiang
Slot filling and intent detection are two highly correlated tasks in spoken language understanding (SLU). Recent SLU research attempts to explore zero-shot prompting techniques in large language models to alleviate the data scarcity problem. Neverthe
Externí odkaz:
http://arxiv.org/abs/2406.10505
Autor:
Wang, Bingbing, Liang, Bin, Feng, Chun-Mei, Zuo, Wangmeng, Bai, Zhixin, Huang, Shijue, Wong, Kam-Fai, Zeng, Xi, Xu, Ruifeng
In real-world conversations, the diversity and ambiguity of stickers often lead to varied interpretations based on the context, necessitating the requirement for comprehensively understanding stickers and supporting multi-tagging. To address this cha
Externí odkaz:
http://arxiv.org/abs/2403.05428
Developing Large Language Models (LLMs) with robust long-context capabilities has been the recent research focus, resulting in the emergence of long-context LLMs proficient in Chinese. However, the evaluation of these models remains underdeveloped du
Externí odkaz:
http://arxiv.org/abs/2403.03514
Autor:
Huang, Shijue, Zhong, Wanjun, Lu, Jianqiao, Zhu, Qi, Gao, Jiahui, Liu, Weiwen, Hou, Yutai, Zeng, Xingshan, Wang, Yasheng, Shang, Lifeng, Jiang, Xin, Xu, Ruifeng, Liu, Qun
The recent trend of using Large Language Models (LLMs) as tool agents in real-world applications underscores the necessity for comprehensive evaluations of their capabilities, particularly in complex scenarios involving planning, creating, and using
Externí odkaz:
http://arxiv.org/abs/2401.17167
Multi-modal intent detection aims to utilize various modalities to understand the user's intentions, which is essential for the deployment of dialogue systems in real-world scenarios. The two core challenges for multi-modal intent detection are (1) h
Externí odkaz:
http://arxiv.org/abs/2401.00424
Chain-of-thought (CoT) is capable of eliciting models to explicitly generate reasoning paths, thus promoting reasoning accuracy and attracting increasing attention. Specifically, zero-shot CoT achieves remarkable improvements in a wide range of reaso
Externí odkaz:
http://arxiv.org/abs/2310.14799
Few-shot and zero-shot entity linking focus on the tail and emerging entities, which are more challenging but closer to real-world scenarios. The mainstream method is the ''retrieve and rerank'' two-stage framework. In this paper, we propose a coarse
Externí odkaz:
http://arxiv.org/abs/2308.03365
Autor:
Qin, Libo, Huang, Shijue, Chen, Qiguang, Cai, Chenran, Zhang, Yudi, Liang, Bin, Che, Wanxiang, Xu, Ruifeng
Multi-modal sarcasm detection has attracted much recent attention. Nevertheless, the existing benchmark (MMSD) has some shortcomings that hinder the development of reliable multi-modal sarcasm detection system: (1) There are some spurious cues in MMS
Externí odkaz:
http://arxiv.org/abs/2307.07135
Consistency Identification has obtained remarkable success on open-domain dialogue, which can be used for preventing inconsistent response generation. However, in contrast to the rapid development in open-domain dialogue, few efforts have been made t
Externí odkaz:
http://arxiv.org/abs/2109.11292
Publikováno v:
In Knowledge-Based Systems 21 June 2024 294