Best of Both Worlds: Towards Improving Temporal Knowledge Base Question Answering via Targeted Fact Extraction

Nithish Kannen, Udit Sharma, Sumit Neelam, Dinesh Khandelwal, Shajith Ikbal, Hima Karanam, L Venkata Subramaniam

Submission Type: Regular Short Paper

Submission Track: Question Answering

Keywords: Temporal KBQA, Fact Extraction, Semantic Parsing, Questional Answering

TL;DR: A novel combination of KBQA and text corpus based QA, where a targeted temporal fact extraction technique is used to assist a KBQA system wherever it fails

Abstract: Temporal question answering (QA) is a special category of complex question answering task that requires reasoning over facts asserting time intervals of events. Previous works have predominately relied on Knowledge Base Question Answering (KBQA) for temporal QA. One of the major challenges faced by these systems is their inability to retrieve all relevant facts due to factors such as incomplete KB and entity/relation linking errors. A failure to fetch even a single fact will block KBQA from computing the answer. Such cases of KB incompleteness are even more profound in the temporal context. To address this issue, we explore an interesting direction where a targeted temporal fact extraction technique is used to assist KBQA whenever it fails to retrieve temporal facts from the KB. We model the extraction problem as an open-domain question answering task using off-the-shelf language models. This way, we target to extract from textual resources those facts that failed to get retrieved from the KB. Experimental results on two temporal QA benchmarks show promising ~30% & ~10% relative improvements in answer accuracies without any additional training cost.

Submission Number: 3236