Corpora for Automatically Learning to Map Natural Language Questions into SQL Queries

Automatically translating natural language into machine-readable instructions is one of major interesting and challenging tasks in Natural Language (NL) Processing. This problem can be addressed by using machine learning algorithms to generate a function that find mappings between natural language and programming language semantics. For this purpose suitable annotated and structured data are required. In this paper, we describe our method to construct and semi-automatically annotate these kinds of data, consisting of pairs of NL questions and SQL queries. Additionally, we describe two different datasets obtained by applying our annotation method to two well-known corpora, GEOQUERIES and RESTQUERIES . Since we believe that syntactic levels are important, we also generate and make available relational pairs represented by means of their syntactic trees whose lexical content has been generalized. We validate the quality of our corpora by experimenting with them and our machine learning m...

• Type: Conference
• Year: 2010
• Where: LREC
• Authors: Alessandra Giordani, Alessandro Moschitti
• Keywords: Education, LREC 2010, Machine Learning, Natural Language, Programming Language Semantics