E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQL

Translating Natural Language Queries into Structured Query Language (Text-to-SQL or NLQ-to-SQL) is a critical task extensively studied by both the natural language processing and database communities, aimed at providing a natural language interface to databases (NLIDB) and lowering the barrier for non-experts. Despite recent advancements made through the use of Large Language Models (LLMs), significant challenges remain. These include handling complex database schemas, resolving ambiguity in user queries, and generating SQL queries with intricate structures that accurately reflect the user's intent. In this work, we introduce E-SQL, a novel pipeline specifically designed to address these challenges through direct schema linking and candidate predicate augmentation. E-SQL enhances the natural language query by incorporating relevant database items (i.e., tables, columns, and values) and conditions directly into the question, bridging the gap between the query and the database structure. The pipeline leverages candidate predicate augmentation to mitigate erroneous or incomplete predicates in generated SQLs. We further investigate the impact of schema filtering, a technique widely explored in previous work, and demonstrate its diminishing returns when applied alongside advanced large language models. Comprehensive evaluations on the BIRD benchmark illustrate that E-SQL achieves competitive performance, particularly excelling in complex queries with a 66.29% execution accuracy on the test set. All code required to reproduce the reported results is publicly available on our GitHub repository.

xDBTagger: Explainable Natural Language Interface to Databases Using Keyword Mappings and Schema Graph

Translating natural language queries (NLQ) into structured query language (SQL) in interfaces to relational databases is a challenging task that has been widely studied by researchers from both the database and natural language processing communities. Numerous works have been proposed to attack the natural language interfaces to databases (NLIDB) problem either as a conventional pipeline-based or an end-to-end deep-learning-based solution. Nevertheless, regardless of the approach preferred, such solutions exhibit black-box nature, which makes it difficult for potential users targeted by these systems to comprehend the decisions made to produce the translated SQL. To this end, we propose xDBTagger, an explainable hybrid translation pipeline that explains the decisions made along the way to the user both textually and visually. We also evaluate xDBTagger quantitatively in three real-world relational databases. The evaluation results indicate that in addition to being fully interpretable, xDBTagger is effective in terms of accuracy and translates the queries more efficiently compared to other state-of-the-art pipeline-based systems up to 10000 times.

DBTagger: Multi-Task Learning for Keyword Mapping in NLIDBs Using Bi-Directional Recurrent Neural Networks

Translating Natural Language Queries (NLQs) to Structured Query Language (SQL) in interfaces deployed in relational databases is a challenging task, which has been widely studied in database community recently. Conventional rule based systems utilize series of solutions as a pipeline to deal with each step of this task, namely stop word filtering, tokenization, stemming/lemmatization, parsing, tagging, and translation. Recent works have mostly focused on the translation step overlooking the earlier steps by using ad-hoc solutions. In the pipeline, one of the most critical and challenging problems is keyword mapping; constructing a mapping between tokens in the query and relational database elements (tables, attributes, values, etc.). We define the keyword mapping problem as a sequence tagging problem, and propose a novel deep learning based supervised approach that utilizes POS tags of NLQs. Our proposed approach, called \textit{DBTagger} (DataBase Tagger), is an end-to-end and schema independent solution, which makes it practical for various relational databases. We evaluate our approach on eight different datasets, and report new state-of-the-art accuracy results, $92.4\%$ on the average. Our results also indicate that DBTagger is faster than its counterparts up to $10000$ times and scalable for bigger databases.