Faithful Temporal Question Answering over Heterogeneous Sources
This work addresses the problem of improving accuracy and faithfulness in temporal question answering for users needing reliable answers from diverse data sources, representing a novel method for known bottlenecks rather than incremental.
The paper tackles the problem of temporal question answering by addressing limitations in neural inference, implicit time handling, and single-source reliance, proposing a system that enforces temporal constraints, handles implicit questions, and integrates heterogeneous sources, achieving superior performance over baselines in experiments.
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.