ComFact is a benchmark for commonsense fact linking, where models are given contexts and trained to identify situationally-relevant commonsense knowledge from KGs. The novel benchmark, C-om-Fact, contains ∼293k in-context relevance annotations for common-sense triplets across four stylistically diverse dialogue and storytelling datasets.
Source: ComFact: A Benchmark for Linking Contextual Commonsense KnowledgePaper | Code | Results | Date | Stars |
---|