BigText-QA: Question Answering over a Large-Scale Hybrid Knowledge Graph

TL;DR

BigText-QA presents a hybrid knowledge graph approach that combines structured KBs and unstructured textual data to improve complex question answering, outperforming existing neural and graph-based systems.

Contribution

It introduces a unified hybrid knowledge graph for QA, integrating structured and unstructured knowledge sources for enhanced question answering capabilities.

Findings

Outperforms DrQA in accuracy

Achieves competitive results with QUEST

Effectively combines structured and unstructured knowledge

Abstract

Answering complex questions over textual resources remains a challenge, particularly when dealing with nuanced relationships between multiple entities expressed within natural-language sentences. To this end, curated knowledge bases (KBs) like YAGO, DBpedia, Freebase, and Wikidata have been widely used and gained great acceptance for question-answering (QA) applications in the past decade. While these KBs offer a structured knowledge representation, they lack the contextual diversity found in natural-language sources. To address this limitation, BigText-QA introduces an integrated QA approach, which is able to answer questions based on a more redundant form of a knowledge graph (KG) that organizes both structured and unstructured (i.e., "hybrid") knowledge in a unified graphical representation. Thereby, BigText-QA is able to combine the best of both worlds$\unicode{x2013}$a canonical set of named entities, mapped to a structured background KB (such as YAGO or Wikidata), as well as an open set of textual clauses providing highly diversified relational paraphrases with rich context information. Our experimental results demonstrate that BigText-QA outperforms DrQA, a neural-network-based QA system, and achieves competitive results to QUEST, a graph-based unsupervised QA system.