most citedSPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding

14 citations · 22 across the 5 of their papers we have counts for

collaborators

5 papers

cs.CL20221 cited

Estimating Soft Labels for Out-of-Domain Intent Detection

Hao Lang, Yinhe Zheng, Jian Sun +3

Out-of-Domain (OOD) intent detection is important for practical dialog systems. To alleviate the issue of lacking OOD training samples, some works propose synthesizing pseudo OOD s…

cs.CL20221 cited

STAR: SQL Guided Pre-Training for Context-dependent Text-to-SQL Parsing

Zefeng Cai, Xiangyu Li, Binyuan Hui +8

In this paper, we propose a novel SQL guided pre-training framework STAR for context-dependent text-to-SQL parsing, which leverages contextual information to enrich natural languag…

cs.CL20226 cited

SUN: Exploring Intrinsic Uncertainties in Text-to-SQL Parsers

Bowen Qin, Lihan Wang, Binyuan Hui +7

This paper aims to improve the performance of text-to-SQL parsing by exploring the intrinsic uncertainties in the neural network based approaches (called SUN). From the data uncert…

cs.CL2022

Towards Generalizable and Robust Text-to-SQL Parsing

Chang Gao, Bowen Li, Wenxuan Zhang +5

Text-to-SQL parsing tackles the problem of mapping natural language questions to executable SQL queries. In practice, text-to-SQL parsers often encounter various challenging scenar…

cs.CL202214 cited

SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding

Wanwei He, Yinpei Dai, Binyuan Hui +6

Pre-training methods with contrastive learning objectives have shown remarkable success in dialog understanding tasks. However, current contrastive learning solely considers the se…