Improving Text-to-SQL Evaluation Methodology (P18-1)

Copied to clipboard

Challenge: Current evaluations of text-to-SQL systems are limited by the way they divide data into training and test sets.
Approach: They propose to standardize and improve existing and new text-to-SQL datasets . they propose a template-based slot-filling baseline that cannot generalize to new queries .
Outcome: The proposed system is competitive with prior work on multiple datasets and can be used on training and test sets.

Similar Papers

Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expect (2022.coling-1)

Copied to clipboard

Challenge: text-to-SQL is a language processing and database-based language processing (NLP) task is to convert natural utterances into SQL queries and its practical application is to build natural language interfaces to database systems.
Approach: They propose to conduct a systematic survey of text-to-SQL to examine the challenges and potential future directions.
Outcome: The proposed system converts natural utterances into SQL queries and is a representative task in semantic parsing.
Exploring Schema Generalizability of Text-to-SQL (2023.findings-acl)

Copied to clipboard

Challenge: Existing text-to-SQL models are limited in their generalizability, despite their performance being over-estimated.
Approach: They propose a framework to generate novel text-to-SQL data via automatic and synchronous (DS, SQL) pair altering.
Outcome: The proposed framework generates text-to-SQL data via automatic and synchronous (DS, SQL) pair altering.
Evaluating Cross-Domain Text-to-SQL Models and Benchmarks (2023.emnlp-main)

Copied to clipboard

Challenge: Text-to-SQL benchmarks are used to evaluate progress made in the field . however, matching a model-generated SQL query to a reference SQL query fails due to various reasons.
Approach: They conduct an extensive evaluation of text-to-SQL benchmarks and re-evaluate some of the top-performing models.
Outcome: The results show that a recent model surpasses the gold standard reference queries in the Spider benchmark in human evaluation.
On the Effectiveness of Automated Metrics for Text Generation Systems (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing evaluation methods lack a sound theoretical foundation for evaluation campaigns . imperfect automated metrics and insufficiently sized test sets are some of the factors that cause uncertainty.
Approach: They propose a theoretical framework that incorporates different sources of uncertainty, such as imperfect automated metrics and insufficiently sized test sets.
Outcome: The proposed model can be leveraged to improve evaluation protocols regarding reliability, robustness, and significance of the evaluation outcome.
Importance of Synthesizing High-quality Data for Text-to-SQL Parsing (2023.findings-acl)

Copied to clipboard

Challenge: Existing text-to-SQL parsers lack the data to perform well with augmented synthetic data.
Approach: They propose a framework that imposes strong typing constraints and incorporates key relationships from schema.
Outcome: The proposed framework improves on the high-quality synthesized SQL and natural language question (NLQ) models have significant accuracy boosts and achieve new state-of-the-art performance on spider.
SQLSpace: A Representation Space for Text-to-SQL to Discover and Mitigate Robustness Gaps (2025.findings-emnlp)

Copied to clipboard

Challenge: SQLSpace is a representation for text-to-SQL examples derived with minimal human intervention.
Approach: They introduce SQLSpace, a human-interpretable, generalizable, compact representation for text-to-SQL examples . they demonstrate that SQLSpace enables analysis that would be difficult with raw examples alone .
Outcome: The proposed representations are human-interpretable and generalizable . they are used to evaluate models with a granularity beyond overall accuracy scores .
Deconstructing NLG Evaluation: Evaluation Practices, Assumptions, and Their Implications (2022.naacl-main)

Copied to clipboard

Challenge: Evaluating natural language generation systems is difficult, as there are many ways to express similar things in text.
Approach: They combine interviews with NLG practitioners to examine ethical considerations and their implications for NLG evaluation.
Outcome: The findings of the study surface goals, community practices, assumptions, and constraints that shape NLG evaluations, and examine their implications and how they embody ethical considerations.
Know What I don’t Know: Handling Ambiguous and Unknown Questions for Text-to-SQL (2023.findings-acl)

Copied to clipboard

Challenge: Existing text-to-SQL parsers generate a plausible SQL query for arbitrary user questions, thereby failing to handle problematic user questions.
Approach: They propose a weakly supervised DTE model for error detection, localization, and explanation.
Outcome: The proposed model achieves the best result on real-world examples and generated examples compared with baselines.
Interactive Text-to-SQL Generation via Editable Step-by-Step Explanations (2023.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to generate SQL from natural language are still making many mistakes . a new interaction mechanism allows users to edit a step-by-step explanation of a query to fix errors.
Approach: They propose a mechanism that allows users to edit a step-by-step explanation of a query to fix errors.
Outcome: The proposed approach can achieve better performance than multiple SOTA approaches on multiple datasets and 24 participants.
Evaluating Historical Text Normalization Systems: How Well Do They Generalize? (N18-2)

Copied to clipboard

Challenge: Historical text normalization systems aim to convert historical wordforms to their modern equivalents . many of these systems have been developed and tested on a single language .
Approach: They propose to use a nave baseline system to evaluate historical text normalization systems . they show that the models generalize well to unseen words in tests on five languages .
Outcome: The proposed models generalize well to unseen words on five languages, but provide no clear benefit over the nave baseline.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations