Výsledky vyhledávání - "Chang, Jinxiong"

Report

Multi-Intent Attribute-Aware Text Matching in Searching

Autor: Li, Mingzhe, Chen, Xiuying, Xiang, Jing, Zhang, Qishen, Ma, Changsheng, Dai, Chenchen, Chang, Jinxiong, Liu, Zhongyi, Zhang, Guannan

Text matching systems have become a fundamental service in most searching platforms. For instance, they are responsible for matching user queries to relevant candidate items, or rewriting the user-input query to a pre-selected high-performing one for

Externí odkaz: http://arxiv.org/abs/2402.07788

Zobrazit plný text záznamu

Report

Harnessing the Power of David against Goliath: Exploring Instruction Data Generation without Using Closed-Source Models

Autor: Wang, Yue, Wang, Xinrui, Li, Juntao, Chang, Jinxiong, Zhang, Qishen, Liu, Zhongyi, Zhang, Guannan, Zhang, Min

Instruction tuning is instrumental in enabling Large Language Models~(LLMs) to follow user instructions to complete various open-domain tasks. The success of instruction tuning depends on the availability of high-quality instruction data. Owing to th

Externí odkaz: http://arxiv.org/abs/2308.12711

Zobrazit plný text záznamu

Report

Keywords and Instances: A Hierarchical Contrastive Learning Framework Unifying Hybrid Granularities for Text Generation

Autor: Li, Mingzhe, Lin, XieXiong, Chen, Xiuying, Chang, Jinxiong, Zhang, Qishen, Wang, Feng, Wang, Taifeng, Liu, Zhongyi, Chu, Wei, Zhao, Dongyan, Yan, Rui

Contrastive learning has achieved impressive success in generation tasks to militate the "exposure bias" problem and discriminatively exploit the different quality of references. Existing works mostly focus on contrastive learning on the instance-lev

Externí odkaz: http://arxiv.org/abs/2205.13346

Zobrazit plný text záznamu