Results 21 to 30 of about 9,267 (223)

A BERT-Based Generation Model to Transform Medical Texts to SQL Queries for Electronic Medical Records: Model Development and Validation

JMIR Medical Informatics, 2021
BackgroundElectronic medical records (EMRs) are usually stored in relational databases that require SQL queries to retrieve information of interest. Effectively completing such queries can be a challenging task for medical experts
Youcheng Pan, Chenghao Wang, Baotian Hu, Yang Xiang, Xiaolong Wang, Qingcai Chen, Junjie Chen, Jingcheng Du   +7 more
doaj   +1 more source

DIR: A Large-Scale Dialogue Rewrite Dataset for Cross-Domain Conversational Text-to-SQL

Applied Sciences, 2023
Semantic co-reference and ellipsis always lead to information deficiency when parsing natural language utterances with SQL in a multi-turn dialogue (i.e., conversational text-to-SQL task).
Jieyu Li, Zhi Chen, Lu Chen, Zichen Zhu, Hanqi Li, Ruisheng Cao, Kai Yu   +6 more
doaj   +1 more source

DuoRAT: Towards Simpler Text-to-SQL Models [PDF]

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021
Recent neural text-to-SQL models can effectively translate natural language questions to corresponding SQL queries on unseen databases. Working mostly on the Spider dataset, researchers have proposed increasingly sophisticated solutions to the problem. Contrary to this trend, in this paper we focus on simplifications.
Scholak, Torsten, Li, Raymond, Bahdanau, Dzmitry, de Vries, Harm, Pal, Chris   +4 more
openaire   +2 more sources

Assessing the utility of text-to-SQL approaches for satisfying software developer information needs [PDF]

, 2023
Software analytics integrated with complex databases can deliver project intelligence into the hands of software engineering (SE) experts for satisfying their information needs.
Hofmann, Martin, Hütterer, Constantin, Mäder, Patrick, Tomova, Mihaela   +3 more
core   +1 more source

Improving Text-to-SQL Evaluation Methodology [PDF]

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2018
To be informative, an evaluation must measure how well systems generalize to realistic unseen data. We identify limitations of and propose improvements to current evaluations of text-to-SQL systems. First, we compare human-generated and automatically generated questions, characterizing properties of queries necessary for real-world applications.
Finegan-Dollak, Catherine, Kummerfeld, Jonathan K., Zhang, Li, Ramanathan, Karthik, Sadasivam, Sesh, Zhang, Rui, Radev, Dragomir   +6 more
openaire   +2 more sources

Features requirement elicitation process for designing a chatbot application

IET Networks, EarlyView., 2022
This article seeks to assist the chatbot community by outlining the characteristics that a chatbot needs to possess and explaining how to create a chatbot for a bank. In order to determine which capabilities are most crucial to ending users, a study of a small sample of chatbot users was conducted.
Nurul Muizzah Johari, Puteri N. E. Nohuddin, Ahmad Hanif Ahmad Baharin, Noor Azuddin Yakob, Mohammad Javad Ebadi   +4 more
wiley   +1 more source

Relation-Aware Graph Transformer for SQL-to-Text Generation

Applied Sciences, 2021
Generating natural language descriptions for structured representation (e.g., a graph) is an important yet challenging task. In this work, we focus on SQL-to-text, a task that maps a SQL query into the corresponding natural language question.
Da Ma, Xingyu Chen, Ruisheng Cao, Zhi Chen, Lu Chen, Kai Yu   +5 more
doaj   +1 more source

KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers [PDF]

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 2021
The goal of database question answering is to enable natural language querying of real-life relational databases in diverse application domains. Recently, large-scale datasets such as Spider and WikiSQL facilitated novel modeling techniques for text-to-SQL parsing, improving zero-shot generalization to unseen databases.
Lee, Chia-Hsuan, Polozov, Oleksandr, Richardson, Matthew   +2 more
openaire   +2 more sources

TypeSQL: Knowledge-based Type-Aware Neural Text-to-SQL Generation [PDF]

, 2018
Interacting with relational databases through natural language helps users of any background easily query and analyze a vast amount of data. This requires a system that understands users' questions and converts them to SQL queries automatically.
Li, Zifan, Radev, Dragomir, Yu, Tao, Zhang, Rui, Zhang, Zilin   +4 more
core   +2 more sources

Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task [PDF]

, 2018
We present Spider, a large-scale, complex and cross-domain semantic parsing and text-to-SQL dataset annotated by 11 college students. It consists of 10,181 questions and 5,693 unique complex SQL queries on 200 databases with multiple tables, covering 138
Li, Irene, Li, Zifan, Ma, James, Radev, Dragomir, Roman, Shanelle, Wang, Dongxu, Yang, Kai, Yao, Qingning, Yasunaga, Michihiro, Yu, Tao, Zhang, Rui, Zhang, Zilin   +11 more
core   +2 more sources