Výsledky vyhledávání

Report

QDA-SQL: Questions Enhanced Dialogue Augmentation for Multi-Turn Text-to-SQL

Autor: Sun, Yinggang, Guo, Ziming, Yu, Haining, Liu, Chuanyi, Li, Xiang, Wang, Bingxuan, Yu, Xiangzhan, Zhao, Tiancheng

Fine-tuning large language models (LLMs) for specific domain tasks has achieved great success in Text-to-SQL tasks. However, these fine-tuned models often face challenges with multi-turn Text-to-SQL tasks caused by ambiguous or unanswerable questions

Externí odkaz: http://arxiv.org/abs/2406.10593

Zobrazit plný text záznamu

Report

CISum: Learning Cross-modality Interaction to Enhance Multimodal Semantic Coverage for Multimodal Summarization

Autor: Zhang, Litian, Zhang, Xiaoming, Guo, Ziming, Liu, Zhipeng

Multimodal summarization (MS) aims to generate a summary from multimodal input. Previous works mainly focus on textual semantic coverage metrics such as ROUGE, which considers the visual content as supplemental data. Therefore, the summary is ineffec

Externí odkaz: http://arxiv.org/abs/2302.09934

Zobrazit plný text záznamu

Akademický článek

Analysis and Assessment of Operation Risk for Hybrid AC/DC Power System based on the Monte Carlo Method

Autor: Hu Xiaojing, Li Qiang, Zhang Hao, Guo Ziming, Zhao Kun, Li Xinpeng

Publikováno v: E3S Web of Conferences, Vol 38, p 04010 (2018)

Based on the Monte Carlo method, an improved risk assessment method for hybrid AC/DC power system with VSC station considering the operation status of generators, converter stations, AC lines and DC lines is proposed. According to the sequential AC/D

Externí odkaz: https://doaj.org/article/a20d234ed6ea4eab9d6454f162d15a58