Výsledky vyhledávání - "Zhang, Longhui"

Report

Chinese Sequence Labeling with Semi-Supervised Boundary-Aware Language Model Pre-training

Autor: Zhang, Longhui, Long, Dingkun, Zhang, Meishan, Zhang, Yanzhao, Xie, Pengjun, Zhang, Min

Chinese sequence labeling tasks are heavily reliant on accurate word boundary demarcation. Although current pre-trained language models (PLMs) have achieved substantial gains on these tasks, they rarely explicitly incorporate boundary information int

Externí odkaz: http://arxiv.org/abs/2404.05560

Zobrazit plný text záznamu

Report

A Two-Stage Adaptation of Large Language Models for Text Ranking

Autor: Zhang, Longhui, Zhang, Yanzhao, Long, Dingkun, Xie, Pengjun, Zhang, Meishan, Zhang, Min

Text ranking is a critical task in information retrieval. Recent advances in pre-trained language models (PLMs), especially large language models (LLMs), present new opportunities for applying them to text ranking. While supervised fine-tuning (SFT)

Externí odkaz: http://arxiv.org/abs/2311.16720

Zobrazit plný text záznamu

Akademický článek

Clinical efficacy of laparoscopic peritoneal vaginoplasty in the treatment of MRKH syndrome

Autor: Qin Chenglu, Shi Jinqiu, Jiang Liping, Wang Huizi, Liang Maolian, Ma Lili, Ren Junxu, Li Xueru, Zhang Longhui, Li Meng

Publikováno v: 生物医学转化, Vol 5, Iss 3, Pp 36-40 (2024)

Objective To investigate the clinical efficacy of laparoscopic peritoneal vaginoplasty (Luohu Type II) in the treatment of Mayer-Rokitansky-Küster-Hauser (MRKH) syndrome. Methods A retrospective analysis was conducted on the clinical data of 221 pat

Externí odkaz: https://doaj.org/article/bbe42b7a60c7425caa2ab58123c11282

Zobrazit plný text záznamu

Report

Hybrid Retrieval and Multi-stage Text Ranking Solution at TREC 2022 Deep Learning Track

Autor: Xu, Guangwei, Zhang, Yangzhao, Zhang, Longhui, Long, Dingkun, Xie, Pengjun, Guo, Ruijie

Large-scale text retrieval technology has been widely used in various practical business scenarios. This paper presents our systems for the TREC 2022 Deep Learning Track. We explain the hybrid text retrieval and multi-stage text ranking method adopte

Externí odkaz: http://arxiv.org/abs/2308.12039

Zobrazit plný text záznamu