
Research Article
BigText-QA: Question Answering over a Large-Scale Hybrid Knowledge Graph
@INPROCEEDINGS{10.1007/978-3-031-52265-9_3, author={Jingjing Xu and Maria Biryukov and Martin Theobald and Vinu Ellampallil Venugopal}, title={BigText-QA: Question Answering over a Large-Scale Hybrid Knowledge Graph}, proceedings={Big Data Technologies and Applications. 13th EAI International Conference, BDTA 2023, Edinburgh, UK, August 23-24, 2023, Proceedings}, proceedings_a={BDTA}, year={2024}, month={1}, keywords={Question Answering Large-Scale Graph Hybrid Knowledge Graph Natural Language Processing}, doi={10.1007/978-3-031-52265-9_3} }
- Jingjing Xu
Maria Biryukov
Martin Theobald
Vinu Ellampallil Venugopal
Year: 2024
BigText-QA: Question Answering over a Large-Scale Hybrid Knowledge Graph
BDTA
Springer
DOI: 10.1007/978-3-031-52265-9_3
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—acanonical set of named entities, mapped to a structured background KB (such as YAGO or Wikidata), as well as anopen set of textual clausesproviding 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.