Výsledky vyhledávání

Report

KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction

Autor: Li, Zixuan, Zeng, Yutao, Zuo, Yuxin, Ren, Weicheng, Liu, Wenxuan, Su, Miao, Guo, Yucan, Liu, Yantao, Li, Xiang, Hu, Zhilei, Bai, Long, Li, Wei, Liu, Yidan, Yang, Pan, Jin, Xiaolong, Guo, Jiafeng, Cheng, Xueqi

In this paper, we propose KnowCoder, a Large Language Model (LLM) to conduct Universal Information Extraction (UIE) via code generation. KnowCoder aims to develop a kind of unified schema representation that LLMs can easily understand and an effectiv

Externí odkaz: http://arxiv.org/abs/2403.07969

Zobrazit plný text záznamu

Report

DSCom: A Data-Driven Self-Adaptive Community-Based Framework for Influence Maximization in Social Networks

Autor: Zuo, Yuxin, Sun, Haojia, Hu, Yongyi, Guo, Jianxiong, Gao, Xiaofeng

Influence maximization aims to find a subset of seeds that maximize the influence spread under a given budget. In this paper, we mainly address the data-driven version of this problem, where the diffusion model is not given but needs to be inferred f

Externí odkaz: http://arxiv.org/abs/2311.11080

Zobrazit plný text záznamu

Report

Incorporating Probing Signals into Multimodal Machine Translation via Visual Question-Answering Pairs

Autor: Zuo, Yuxin, Li, Bei, Lv, Chuanhao, Zheng, Tong, Xiao, Tong, Zhu, Jingbo

This paper presents an in-depth study of multimodal machine translation (MMT), examining the prevailing understanding that MMT systems exhibit decreased sensitivity to visual information when text inputs are complete. Instead, we attribute this pheno

Externí odkaz: http://arxiv.org/abs/2310.17133

Zobrazit plný text záznamu