R
Rui Zhang
Researcher at Pennsylvania State University
Publications - 54
Citations - 2811
Rui Zhang is an academic researcher from Pennsylvania State University. The author has contributed to research in topics: SQL & Automatic summarization. The author has an hindex of 22, co-authored 54 publications receiving 1765 citations. Previous affiliations of Rui Zhang include IBM & Yale University.
Papers
More filters
Posted Content
Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task
Tao Yu,Rui Zhang,Kai Yang,Michihiro Yasunaga,Dongxu Wang,Zifan Li,James Ma,Irene Li,Qingning Yao,Shanelle Roman,Zilin Zhang,Dragomir R. Radev +11 more
TL;DR: This work defines a new complex and cross-domain semantic parsing and text-to-SQL task so that different complicated SQL queries and databases appear in train and test sets and experiments with various state-of-the-art models show that Spider presents a strong challenge for future research.
Proceedings ArticleDOI
Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task
Tao Yu,Rui Zhang,Kai Yang,Michihiro Yasunaga,Dongxu Wang,Zifan Li,James Ma,Irene Li,Qingning Yao,Shanelle Roman,Zilin Zhang,Dragomir R. Radev +11 more
TL;DR: Spider as discussed by the authors is a large-scale complex and cross-domain semantic parsing and text-to-SQL dataset annotated by 11 college students and consists of 10,181 questions and 5,693 unique complex SQL queries.
Proceedings ArticleDOI
Improving text-to-SQL evaluation methodology
Catherine Finegan-Dollak,Jonathan K. Kummerfeld,Li Zhang,Karthik Ramanathan,Sesh Sadasivam,Rui Zhang,Dragomir R. Radev +6 more
TL;DR: It is shown that the current division of data into training and test sets measures robustness to variations in the way questions are asked, but only partially tests how well systems generalize to new queries, and proposes a complementary dataset split for evaluation of future work.
Proceedings ArticleDOI
TypeSQL: Knowledge-Based Type-Aware Neural Text-to-SQL Generation
TL;DR: This article presented a novel approach TypeSQL which formats the problem as a slot filling task in a more reasonable way and utilizes type information to better understand rare entities and numbers in the questions.
Proceedings ArticleDOI
SyntaxSqlnet: Syntax tree networks for complex and cross-domain text-to-SQL task
TL;DR: Experimental results show that SyntaxSQLNet can handle a significantly greater number of complex SQL examples than prior work, outperforming the previous state-of-the-art model by 9.5% in exact matching accuracy.