Schemaless Queries over Document Tables with Dependencies

Abstract

Unstructured enterprise data such as reports, manuals and guidelines often contain tables. The traditional way of integrating data from these tables is through a two-step process of table detection/extraction and mapping the table layouts to an appropriate schema. This can be an expensive process. In this paper we show that by using semantic technologies (RD-F/SPARQL and database dependencies) paired with a simple but powerful way to transform tables with non-relational layouts, it is possible to offer query answering services over these tables with minimal manual work or domain-specific mappings. Our method enables users to exploit data in tables embedded in documents with little effort, not only for simple retrieval queries, but also for structured queries that require joining multiple interrelated tables.

AIT-QA: Question Answering Dataset over Complex Tables in the Airline Industry

“…The tabular data format is commonly used in digital documents such as PDFs and HTMLs to store semistructured information (Canim et al, 2019; Zhang and * Work done while author was working at IBM. Balog, 2018;Pasupat and Liang, 2015).…”