CAR: Conceptualization-Augmented Reasoner for Zero-Shot Commonsense Question Answering
Weiqi Wang, Tianqing Fang, Wenxuan Ding, Baixuan Xu, Xin Liu, Yangqiu Song, Antoine Bosselut · 2023
The task of zero-shot commonsense question answering evaluates models on their capacity to reason about general scenarios beyond those presented in specific datasets.Existing approaches for tackling this task leverage external knowledge from CommonSense Knowledge Bases (CSKBs) by pre-training the model on synthetic QA pairs constructed from CSKBs.In these approaches, negative examples (distractors) are formulated by randomly sampling from CSKBs using fairly primitive keyword constraints.However, two bottlenecks limit these approaches: the inherent incompleteness of CSKBs limits the semantic coverage of synthetic QA pairs, and the lack of human annotations makes the sampled negative examples potentially uninformative and contradictory.To tackle these limitations above, we propose Conceptualization-Augmented Reasoner (CAR), a zero-shot commonsense questionanswering framework that fully leverages the power of conceptualization.Specifically, CAR abstracts a commonsense knowledge triple to many higher-level instances, which increases the coverage of the CSKB and expands the ground-truth answer space, reducing the likelihood of selecting false-negative distractors.Extensive experiments demonstrate that CAR more robustly generalizes to answering questions about zero-shot commonsense scenarios than existing methods, including large language models, such as GPT3.5 and Chat-GPT.Our code, data, and model checkpoints are available at https://github.com/HKUST- KnowComp/CAR.(PersonX played a football game, xWant, take a rest) (played a football game, IsA, Sport) (played a football game, IsA, Tiring event) … (played a football game, IsA, Exercise) Original Knowledge Triple Conceptualization Relations (PersonX (do) Sport, xWant, take a rest) (PersonX (do) Tiring event, xWant, take a rest) … (PersonX (do) Exercise, xWant, take a rest)