Results 81 to 90 of about 9,267 (223)

Reliable Text-to-SQL with Adaptive Abstention

Proceedings of the ACM on Management of Data
Large language models (LLMs) have revolutionized natural language interfaces for databases, particularly in text-to-SQL conversion. However, current approaches often generate unreliable outputs when faced with ambiguity or insufficient context. We present Reliable Text-to-SQL (RTS), a novel framework that enhances query generation reliability
Kaiwen Chen, Yueting Chen, Nick Koudas, Xiaohui Yu   +3 more
openaire   +2 more sources

Improving Text-to-SQL with Schema Dependency Learning

, 2021
Text-to-SQL aims to map natural language questions to SQL queries. The sketch-based method combined with execution-guided (EG) decoding strategy has shown a strong performance on the WikiSQL benchmark. However, execution-guided decoding relies on database execution, which significantly slows down the inference process and is hence unsatisfactory for ...
Hui, Binyuan, Shi, Xiang, Geng, Ruiying, Li, Binhua, Li, Yongbin, Sun, Jian, Zhu, Xiaodan   +6 more
openaire   +2 more sources

Data-Anonymous Encoding for Text-to-SQL Generation [PDF]

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 2019
Sur la génération texte vers SQL, l'énoncé d'entrée contient généralement beaucoup de jetons liés aux noms de colonnes ou aux cellules du tableau, appelés jetons liés à la table. Ces jetons liés à la table sont gênants pour l'analyseur sémantique neuronal en aval car ils apportent une sémantique complexe et entravent le partage des exemples de ...
Zhen Dong, Shizhao Sun, Hongzhi Liu, Jian–Guang Lou, Dongmei Zhang   +4 more
openaire   +1 more source

Exploring Chain-of-Thought Style Prompting for Text-to-SQL

, 2023
In-context learning with large language models (LLMs) has recently caught increasing attention due to its superior few-shot performance on various tasks. However, its performance on text-to-SQL parsing still has much room for improvement.
Chen, Ziru, Deng, Xiang, Sun, Huan, Tai, Chang-You, Zhang, Tianshu   +4 more
core  

Curse or Blessing: Investigating the Influence of Firms’ Artificial Intelligence Adoption on Employee Job Satisfaction

Journal of Management Studies, EarlyView.
Abstract Artificial intelligence’s (AI’s) growing influence in business has introduced a pivotal shift in workplace dynamics. However, the understanding of how AI adoption influences employee job satisfaction remains inconclusive. Drawing on job characteristics theory, we argue that with increasing levels of adoption, the relationship between employees’
Colin Schulz, David Bendig, Antonio Bräunche, Bastian Kindermann   +3 more
wiley   +1 more source

ETM: Modern Insights into Perspective on Text-to-SQL Evaluation in the Age of Large Language Models

Future Internet
The task of Text-to-SQL enables anyone to retrieve information from SQL databases using natural language. While this task has made substantial progress, the two primary evaluation metrics—Execution Accuracy (EXE) and Exact Set Matching Accuracy (ESM ...
Benjamin G. Ascoli, Yasoda Sai Ram Kandikonda, Jinho D. Choi   +2 more
doaj   +1 more source

HIE-SQL: History Information Enhanced Network for Context-Dependent Text-to-SQL Semantic Parsing [PDF]

, 2022
Yanzhao Zheng, Haibin Wang, Baohua Dong, Xingjun Wang, Changshan Li   +4 more
openalex   +1 more source

A validity evaluation of lexicon‐based sentiment analysis of medical students' clinical performance from in‐training evaluation reports

Medical Education, EarlyView.
Abstract Introduction Assessment of clinical performance has traditionally been a numbers game based upon Likert scale ratings. But, thanks to advances in the science of natural language processing (NLP), it is now possible to incorporate rich narrative data into assessment.
Irene Ma, Mike Paget, Janeve Desy, Adrian Harvey, Glenda Bendiak, Christopher Naugler, Kevin McLaughlin   +6 more
wiley   +1 more source

Fine-tuning text-to-SQL models with reinforcement-learning training objectives

Natural Language Processing Journal
Text-to-SQL is an important natural language processing task that helps users automatically convert natural language queries into formal SQL code. While transformer-based models have pushed text-to-SQL to unprecedented accuracy levels in recent years ...
Xuan-Bang Nguyen, Xuan-Hieu Phan, Massimo Piccardi   +2 more
doaj   +1 more source

Mapping Labor Demand for Data‐Intensive Work in the United Kingdom, Canada, and the United States

Review of Income and Wealth, Volume 72, Issue 1, February 2026.
ABSTRACT The paper makes three main contributions. First, it develops an NLP‐based methodology to identify data‐intensive skills in job advertisements at scale. Second, it operationalizes a transparent indicator of data intensity for occupations and industries. Third, by applying the method to job advertisements from the United Kingdom, Canada, and the
Julia Schmidt, Graham Pilgrim, Annabelle Mourougane   +2 more
wiley   +1 more source