Solo: Data Discovery Using Natural Language Questions Via A Self-Supervised Approach

TL;DR

Solo is a self-supervised data discovery system that enables natural language question-based data search without requiring expensive training data, outperforming existing methods on benchmark datasets.

Contribution

The paper introduces a self-supervised training approach for data discovery systems, eliminating the need for human-labeled data and integrating multiple strategies into the Solo system.

Findings

Outperforms state-of-the-art on benchmark datasets

Effective self-supervised training strategies developed

System end-to-end solution demonstrated

Abstract

Most deployed data discovery systems, such as Google Datasets, and open data portals only support keyword search. Keyword search is geared towards general audiences but limits the types of queries the systems can answer. We propose a new system that lets users write natural language questions directly. A major barrier to using this learned data discovery system is it needs expensive-to-collect training data, thus limiting its utility. In this paper, we introduce a self-supervised approach to assemble training datasets and train learned discovery systems without human intervention. It requires addressing several challenges, including the design of self-supervised strategies for data discovery, table representation strategies to feed to the models, and relevance models that work well with the synthetically generated questions. We combine all the above contributions into a system, Solo, that solves the problem end to end. The evaluation results demonstrate the new techniques outperform state-of-the-art approaches on well-known benchmarks. All in all, the technique is a stepping stone towards building learned discovery systems. The code is open-sourced at https://github.com/TheDataStation/solo