Answering Questions with Complex Semantic Constraints on Open Knowledge Bases
Authors:
Open Access
- 17 October 2015
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1301-1310
Abstract
A knowledge-based question-answering system (KB-QA) is one that answers natural language questions with information stored in a large-scale knowledge base (KB). Existing KB-QA systems are either powered by curated KBs in which factual knowledge is encoded in entities and relations with well-structured schemas, or by open KBs, which contain assertions represented in the form of triples (e.g., subject; relation phrase; argument). We show that both approaches fall short in answering questions with complex prepositional or adverbial constraints. We propose using n-tuple assertions, which are assertions with an arbitrary number of arguments, and n-tuple open KB (nOKB), which is an open knowledge base of n-tuple assertions. We present TAQA, a novel KB-QA system that is based on an nOKB and illustrate via experiments how TAQA can effectively answer complex questions with rich semantic constraints. Our work also results in a new open KB containing 120M n-tuple assertions and a collection of 300 labeled complex questions, which is made publicly available for further research.Keywords
Funding Information
- Research Grants Council, University Grants Committee, Hong Kong (HKU712712E)
This publication has 10 references indexed in Scilit:
- Canonicalizing Open Knowledge Bases2014
- Open question answering over curated and extracted knowledge bases2014
- Semantic Parsing via Paraphrasing2014
- Information Extraction over Structured Data: Question Answering with Freebase2014
- Knowledge-Based Question Answering as Machine Translation2014
- ClausIE2013
- Probase2012
- A framework for merging and ranking of answers in DeepQAIBM Journal of Research and Development, 2012
- Freebase2008
- DBpedia: A Nucleus for a Web of Open Data2007