TEQUILA: Temporal Question Answering over Knowledge Bases

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.

arXiv commentCIKM 2018 Short Paper

References in corpus (2)

• Learning Dependency-Based Compositional Semantics
• Enhancing QA Systems with Complex Temporal Question Processing Capabilities

Cited by in corpus (10)

• QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension
• Complex Temporal Question Answering on Knowledge Graphs
• Representation Learning for Dynamic Graphs: A Survey
• A Dataset for Answering Time-Sensitive Questions
• TwiRGCN: Temporally Weighted Graph Convolution for Question Answering over Temporal Knowledge Graphs
• TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion
• Temporal Knowledge Graph Reasoning Triggered by Memories
• Template-Based Question Answering over Linked Geospatial Data
• ForecastQA: A Question Answering Challenge for Event Forecasting with Temporal Text Data
• Complex Knowledge Base Question Answering: A Survey