DBPal

Abstract

In this demo, we present DBPal, a novel data exploration tool with a natural language interface. DBPal leverages recent advances in deep models to make query understanding more robust in the following ways: First, DBPal uses novel machine translation models to translate natural language statements to SQL, making the translation process more robust to paraphrasing and linguistic variations. Second, to support the users in phrasing questions without knowing the database schema and the query features, DBPal provides a learned auto-completion model that suggests to users partial query extensions during query formulation and thus helps to write complex queries.

SpeakQL: Towards Speech-driven Multimodal Querying of Structured Data

“…This is because the major difficulty metric for spoken querying and typed querying are different. The difficulty for typed NLI lies in inferring join paths and building nested queries [9,10]. While for spoken querying, the difficulty metric is the number of tokens in the query.…”

Structuring Natural Language to Query Language: A Review

“…The highlight of this approach is the use of the max-flow algorithm which collects solutions and also disregards those solutions that disobey semantic constraints. The proposed technology in [6] addresses challenges like the lack of good visual interactive tools and the fact that NLIDBs have still not made sufficient progress into practical and commercial products. This model has a considerable leverage on DNN models as the core of its NL interface system.…”