Towards a theory of natural language interfaces to databases

Abstract

The need for Natural Language Interfaces (NLIs) to databases has become increasingly acute as more nontechnical people access information through their web browsers, PDAs and cell phones. Yet NLIs are only usable if they map natural language questions to SQL queries correctly. We introduce the Precise NLI [2], which reduces the semantic interpretation challenge in NLIs to a graph matching problem. Precise uses the max-flow algorithm to efficiently solve this problem. Each max-flow solution corresponds to a possible semantic interpretation of the sentence. precise collects max-flow solutions, discards the solutions that do not obey syntactic constraints and retains the rest as the basis for generating SQL queries corresponding to the question q. The syntactic information is extracted from the parse tree corresponding to the given question which is computed by a statistical parser [1]. For a broad, well-defined class of semantically tractable natural language questions, Precise is guaranteed to map each question to the corresponding SQL query.

CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases

“…Text-to-SQL generation Text-to-SQL generation has been studied for decades in both DB and NLP communities. (Warren and Pereira, 1982;Zettlemoyer and Collins, 2005;Popescu et al, 2003;Li et al, 2006;Li and Jagadish, 2014;Iyer et al, 2017;Zhong et al, 2017;Xu et al, 2017;Yu et al, 2018a;Dong and Lapata, 2018;Finegan-Dollak et al, 2018;Guo et al, 2019;Bogin et al, 2019). However, the majority of previous work focus on converting a single, complex question into its corresponding SQL query.…”

Web Table Extraction, Retrieval and Augmentation

“…One of the main challenges of QA on tables, shared by both scenarios, is how to match the unstructured query with the (semi-)structured information in tables. Question answering on tables is also closely related to work on natural language interfaces to databases, where the idea is that users can issue natural language queries, instead of using formal structured query languages (like SQL), for accessing databases Androutsopoulos et al (1995); Li and Jagadish (2014); Li et al (2005); Popescu et al (2003). Semantic parsing is the task of parsing natural language queries into a formal representation.…”

An open source and modular search engine for biomedical literature retrieval

“…In information retrieval, many studies [27][28][29][30][31][32] have attempted over the years to facilitate the search process for users by creating methods capable of handling more complex, natural language-like queries. Usually, queries submitted to scientific databases have to conform to a specific pattern, such as being written in a formal query language or requiring the use of controlled vocabularies.…”