KU-DMIS at EHRSQL 2024:Generating SQL query via question templatization in EHR

• URL: http://arxiv.org/abs/2406.00014v2
• Date: Wed, 19 Jun 2024 16:21:46 GMT
• Title: KU-DMIS at EHRSQL 2024:Generating SQL query via question templatization in EHR
• Authors: Hajung Kim, Chanhwi Kim, Hoonick Lee, Kyochul Jang, Jiwoo Lee, Kyungjae Lee, Gangwoo Kim, Jaewoo Kang,
• Abstract summary: We introduce a novel text-to-domain framework that robustly handles out-of-domain questions and the generated queries with query execution. We use a powerful large language model (LLM), fine-tuned GPT-3.5 with detailed prompts involving the table schemas of the EHR database system.
• Score: 17.998140363824174
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Transforming natural language questions into SQL queries is crucial for precise data retrieval from electronic health record (EHR) databases. A significant challenge in this process is detecting and rejecting unanswerable questions that request information beyond the database's scope or exceed the system's capabilities. In this paper, we introduce a novel text-to-SQL framework that robustly handles out-of-domain questions and verifies the generated queries with query execution.Our framework begins by standardizing the structure of questions into a templated format. We use a powerful large language model (LLM), fine-tuned GPT-3.5 with detailed prompts involving the table schemas of the EHR database system. Our experimental results demonstrate the effectiveness of our framework on the EHRSQL-2024 benchmark benchmark, a shared task in the ClinicalNLP workshop. Although a straightforward fine-tuning of GPT shows promising results on the development set, it struggled with the out-of-domain questions in the test set. With our framework, we improve our system's adaptability and achieve competitive performances in the official leaderboard of the EHRSQL-2024 challenge.

Related papers

• Bridging the Gap: Enabling Natural Language Queries for NoSQL Databases through Text-to-NoSQL Translation [25.638927795540454]
  We introduce the Text-to-No task, which aims to convert natural language queries into accessible queries. To promote research in this area, we released a large-scale and open-source dataset for this task, named TEND (short interfaces for Text-to-No dataset) We also designed a SLM (Small Language Model)-assisted and RAG (Retrieval-augmented Generation)-assisted multi-step framework called SMART, which is specifically designed for Text-to-No conversion.
  arXiv  Detail & Related papers  (2025-02-16T17:01:48Z)
• A Survey of Large Language Model-Based Generative AI for Text-to-SQL: Benchmarks, Applications, Use Cases, and Challenges [0.7889270818022226]
  Text-to-one systems facilitate smooth interaction with databases by translating natural language queries into Structured Query Language (technical) This survey provides an overview of the evolution of AI-driven text-to-one systems. We examine the applications of text-to-one in domains like healthcare, education, and finance.
  arXiv  Detail & Related papers  (2024-12-06T17:36:28Z)
• E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQL [1.187832944550453]
  We introduce E-Seek, a novel pipeline specifically designed to address these challenges through direct schema linking and candidate predicate augmentation. E-Seek enhances the natural language query by incorporating relevant database items (i.e., tables, columns, and values) and conditions directly into the question andsql construction plan, bridging the gap between the query and the database structure. Comprehensive evaluations illustrate that E-Seek achieves competitive performance, particularly excelling in complex queries with a 66.29% execution accuracy on the test set.
  arXiv  Detail & Related papers  (2024-09-25T09:02:48Z)
• Hybrid Querying Over Relational Databases and Large Language Models [8.926173054003547]
  We present the first cross-domain benchmark, SWAN, containing 120 beyond-Database questions over four real-world databases. We present two solutions: one based on schema expansion and the other based on user defined functions. Our evaluation demonstrates that using GPT-4 Turbo with few-shot prompts, one can achieves up to 40.0% in execution accuracy and 48.2% in data factuality.
  arXiv  Detail & Related papers  (2024-08-01T19:29:18Z)
• BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval [54.54576644403115]
  Many complex real-world queries require in-depth reasoning to identify relevant documents. We introduce BRIGHT, the first text retrieval benchmark that requires intensive reasoning to retrieve relevant documents. Our dataset consists of 1,384 real-world queries spanning diverse domains, such as economics, psychology, mathematics, and coding.
  arXiv  Detail & Related papers  (2024-07-16T17:58:27Z)
• LG AI Research & KAIST at EHRSQL 2024: Self-Training Large Language Models with Pseudo-Labeled Unanswerable Questions for a Reliable Text-to-SQL System on EHRs [58.59113843970975]
  Text-to-answer models are pivotal for making Electronic Health Records accessible to healthcare professionals without knowledge. We present a self-training strategy using pseudo-labeled un-answerable questions to enhance the reliability of text-to-answer models for EHRs.
  arXiv  Detail & Related papers  (2024-05-18T03:25:44Z)
• Selecting Query-bag as Pseudo Relevance Feedback for Information-seeking Conversations [76.70349332096693]
  Information-seeking dialogue systems are widely used in e-commerce systems. We propose a Query-bag based Pseudo Relevance Feedback framework (QB-PRF) It constructs a query-bag with related queries to serve as pseudo signals to guide information-seeking conversations.
  arXiv  Detail & Related papers  (2024-03-22T08:10:32Z)
• SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL (extended) [53.95151604061761]
  This paper introduces the framework for enhancing Text-to- filtering using large language models (LLMs) With few-shot prompting, we explore the effectiveness of consistency decoding with execution-based error analyses. With instruction fine-tuning, we delve deep in understanding the critical paradigms that influence the performance of tuned LLMs.
  arXiv  Detail & Related papers  (2023-05-26T21:39:05Z)
• UNITE: A Unified Benchmark for Text-to-SQL Evaluation [72.72040379293718]
  We introduce a UNIfied benchmark for Text-to-domain systems. It is composed of publicly available text-to-domain datasets and 29K databases. Compared to the widely used Spider benchmark, we introduce a threefold increase in SQL patterns.
  arXiv  Detail & Related papers  (2023-05-25T17:19:52Z)
• Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering [78.9863753810787]
  A large amount of world's knowledge is stored in structured databases. query languages can answer questions that require complex reasoning, as well as offering full explainability.
  arXiv  Detail & Related papers  (2021-08-05T22:04:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.