TEQUILA: Temporal Question Answering over Knowledge Bases
Authors:
- Zhen JiaZJZhen Jia
- Abdalghani AbujabalAAAbdalghani Abujabal
- Rishiraj Saha RoyRRRishiraj Saha Roy
- Jannik StroetgenJSJannik Stroetgen
- Gerhard WeikumGWGerhard Weikum
Preprint
Abstract
Question answering over knowledge bases (KB-QA) poses challenges in handling complex questions that need to be decomposed into sub-questions. An important case, addressed here, is that of temporal questions, where cues for temporal relations need to be discovered and handled. We present TEQUILA, an enabler method for temporal QA that can run on top of any KB-QA engine. TEQUILA has four stages. It detects if a question has temporal intent. It decomposes and rewrites the question into non-temporal sub-questions and temporal constraints. Answers to sub-questions are then retrieved from the underlying KB-QA engine. Finally, TEQUILA uses constraint reasoning on temporal intervals to compute final answers to the full question. Comparisons against state-of-the-art baselines show the viability of our method.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Never-Ending Learning for Open-Domain Question Answering over Knowledge Bases2018
- Automated Template Generation for Question Answering over Knowledge Graphs2017
- More Accurate Question Answering on Freebase2015
- Answering Questions with Complex Semantic Constraints on Open Knowledge Bases2015
- Large-scale Semantic Parsing without Question-Answer PairsTransactions of the Association for Computational Linguistics, 2014
- Open question answering over curated and extracted knowledge bases2014
- Learning Dependency-Based Compositional SemanticsComputational Linguistics, 2013
- Template-based question answering over RDF data2012
- Enhancing QA Systems with Complex Temporal Question Processing CapabilitiesJournal of Artificial Intelligence Research, 2009
- Improving search relevance for implicitly temporal queries2009