Analyzing Commonsense Emergence in Few-shot Knowledge Models
doi:10.24432/C5NK5J
TL;DR
We train commonsense knowledge models in few-shot settings to study the emergence of their commonsense representation abilities. Recently, commonsense knowledge models --- pretrained language models (LM) fine-tuned on knowledge graph (KG) tuples --- showed that considerable amounts of commonsense knowledge can be encoded in the parameters of large language models. However, as parallel studies show that LMs are poor hypothesizers of declarative commonsense relationships on their own, it remains unclear whether this knowledge is learned during pretraining or from fine-tuning on KG examples. To investigate this question, we train commonsense knowledge models in few-shot settings to study the emergence of their commonsense representation abilities. Our results show that commonsense knowledge models can rapidly adapt from limited examples, indicating that KG fine-tuning serves to learn an interface to encoded knowledge learned during pretraining. Importantly, our analysis of absolute, angular, and distributional parameter changes during few-shot fine-tuning provides novel insights into how this interface is learned.
Citation
@inproceedings{
da2021analyzing,
title={Analyzing Commonsense Emergence in Few-shot Knowledge Models},
author={Jeff Da and Ronan Le Bras and Ximing Lu and Yejin Choi and Antoine Bosselut},
booktitle={3rd Conference on Automated Knowledge Base Construction},
year={2021},
url={https://openreview.net/forum?id=StHCELh9PVE},
doi={10.24432/C5NK5J}
}