Faithful Temporal Question Answering over Heterogeneous Sources
Open Access
- 13 May 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2052-2063
Abstract
Temporal question answering (QA) involves time constraints, with phrases such as "... in 2019" or "... before COVID". In the former, time is an explicit condition, in the latter it is implicit. State-of-the-art methods have limitations along three dimensions. First, with neural inference, time constraints are merely soft-matched, giving room to invalid or inexplicable answers. Second, questions with implicit time are poorly supported. Third, answers come from a single source: either a knowledge base (KB) or a text corpus. We propose a temporal QA system that addresses these shortcomings. First, it enforces temporal constraints for faithful answering with tangible evidence. Second, it properly handles implicit questions. Third, it operates over heterogeneous sources, covering KB, text and web tables in a unified manner. The method has three stages: (i) understanding the question and its temporal conditions, (ii) retrieving evidence from all sources, and (iii) faithfully answering the question. As implicit questions are sparse in prior benchmarks, we introduce a principled method for generating diverse questions. Experiments show superior performance over a suite of baselines.Keywords
All Related Versions
Funding Information
- NSFC (62276215, 62272398)
This publication has 44 references indexed in Scilit:
- Complex Question Answering Over Temporal Knowledge Graphs2022
- Modeling Temporal-Sensitive Information for Complex Question Answering over Knowledge Graphs2022
- Temporal Knowledge Graph Completion Using Box EmbeddingsProceedings of the AAAI Conference on Artificial Intelligence, 2022
- EvoKG2022
- Improving Time Sensitivity for Question Answering over Temporal Knowledge Graphs2022
- Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering2021
- Question Answering Over Temporal Knowledge Graphs2021
- Deriving Validity Time in Knowledge Graph2018
- When a Knowledge Base Is Not Enough2016
- TAGME2010