English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Research in Text-to-SQL conversion has been largely benchmarked againstdatasets where each text query corresponds to one correct SQL. However, naturallanguage queries over real-life databases frequently involve significantambiguity about the intended SQL due to overlapping schema names and multipleconfusing relationship paths. To bridge this gap, we develop a novel benchmarkcalled AmbiQT with over 3000 examples where each text is interpretable as twoplausible SQLs due to lexical and/or structural ambiguity.  When faced with ambiguity, an ideal top-$k$ decoder should generate all validinterpretations for possible disambiguation by the user. We evaluate severalText-to-SQL systems and decoding algorithms, including those employingstate-of-the-art LLMs, and find them to be far from this ideal. The primaryreason is that the prevalent beam search algorithm and its variants, treat SQLqueries as a string and produce unhelpful token-level diversity in the top-$k$.  We propose LogicalBeam, a new decoding algorithm that navigates the SQL logicspace using a blend of plan-based template generation and constrainedinfilling. Counterfactually generated plans diversify templates whilein-filling with a beam-search that branches solely on schema names providesvalue diversity. LogicalBeam is up to $2.5$ times more effective thanstate-of-the-art models at generating all candidate SQLs in the top-$k$ rankedoutputs. It also enhances the top-$5$ Exact and Execution Match Accuracies onSPIDER and Kaggle DBQA.

Benchmarking and Improving Text-to-SQL Generation under Ambiguity