Zobrazeno 1 - 10
of 407
pro vyhledávání: '"Cao, Tianyu"'
As large language models (LLMs) expand the power of natural language processing to handle long inputs, rigorous and systematic analyses are necessary to understand their abilities and behavior. A salient application is summarization, due to its ubiqu
Externí odkaz:
http://arxiv.org/abs/2404.06162
Autor:
Liu, Xin, Li, Zheng, Gao, Yifan, Yang, Jingfeng, Cao, Tianyu, Wang, Zhengyang, Yin, Bing, Song, Yangqiu
The goal of session-based recommendation in E-commerce is to predict the next item that an anonymous user will purchase based on the browsing and purchase history. However, constructing global or local transition graphs to supplement session data can
Externí odkaz:
http://arxiv.org/abs/2312.16199
Autor:
Wang, Ruijie, Li, Zheng, Yang, Jingfeng, Cao, Tianyu, Zhang, Chao, Yin, Bing, Abdelzaher, Tarek
This paper investigates cross-lingual temporal knowledge graph reasoning problem, which aims to facilitate reasoning on Temporal Knowledge Graphs (TKGs) in low-resource languages by transfering knowledge from TKGs in high-resource ones. The cross-lin
Externí odkaz:
http://arxiv.org/abs/2303.14898
Autor:
Yu, Changlong, Wang, Weiqi, Liu, Xin, Bai, Jiaxin, Song, Yangqiu, Li, Zheng, Gao, Yifan, Cao, Tianyu, Yin, Bing
Understanding users' intentions in e-commerce platforms requires commonsense knowledge. In this paper, we present FolkScope, an intention knowledge graph construction framework to reveal the structure of humans' minds about purchasing items. As commo
Externí odkaz:
http://arxiv.org/abs/2211.08316
Autor:
Jiang, Haoming, Cao, Tianyu, Li, Zheng, Luo, Chen, Tang, Xianfeng, Yin, Qingyu, Zhang, Danqing, Goutam, Rahul, Yin, Bing
E-commerce query understanding is the process of inferring the shopping intent of customers by extracting semantic meaning from their search queries. The recent progress of pre-trained masked language models (MLM) in natural language processing is ex
Externí odkaz:
http://arxiv.org/abs/2210.03915
Autor:
Cao, Tianyu1,2 (AUTHOR), Sun, Qian3 (AUTHOR), Shi, Xiaoqin4 (AUTHOR), Lin, Xiuke5 (AUTHOR), Lin, Qingyuan1 (AUTHOR), Zhu, Jinchao1 (AUTHOR), Xu, Junhao2 (AUTHOR), Cui, Di2 (AUTHOR) cuidi@sjtu.edu.cn, Shi, Youwei2,6 (AUTHOR) shiyouwei@alumni.sjtu.edu.cn, Jing, Yifeng2 (AUTHOR) jingyifeng@sjtu.edu.cn, Guo, Wenhuan1 (AUTHOR) wenhuan1130@sina.com
Publikováno v:
Biological Procedures Online. 7/5/2024, Vol. 26 Issue 1, p1-13. 13p.
Autor:
Huang, Zijie, Li, Zheng, Jiang, Haoming, Cao, Tianyu, Lu, Hanqing, Yin, Bing, Subbian, Karthik, Sun, Yizhou, Wang, Wei
Predicting missing facts in a knowledge graph (KG) is crucial as modern KGs are far from complete. Due to labor-intensive human labeling, this phenomenon deteriorates when handling knowledge represented in various languages. In this paper, we explore
Externí odkaz:
http://arxiv.org/abs/2203.14987
Autor:
Sun, Xiaofeng, Hu, Tianqing, Bai, Yuexia, Cao, Tianyu, Wang, Shuai, Hu, Wei, Yang, Huan, Luo, Xiliang, Cui, Min
Publikováno v:
In Biosensors and Bioelectronics 15 June 2024 254
We study distributed (strongly convex) optimization problems over a network of agents, with no centralized nodes. The loss functions of the agents are assumed to be \textit{similar}, due to statistical data similarity or otherwise. In order to reduce
Externí odkaz:
http://arxiv.org/abs/2110.12347
Autor:
Zhang, Danqing, Li, Zheng, Cao, Tianyu, Luo, Chen, Wu, Tony, Lu, Hanqing, Song, Yiwei, Yin, Bing, Zhao, Tuo, Yang, Qiang
Publikováno v:
The 30th ACM International Conference on Information and Knowledge Management (CIKM 2021, Applied Research Track)
We study the problem of query attribute value extraction, which aims to identify named entities from user queries as diverse surface form attribute values and afterward transform them into formally canonical forms. Such a problem consists of two phas
Externí odkaz:
http://arxiv.org/abs/2108.08468