An Empirical Investigation of Commonsense Self-Supervision with Knowledge Graphs
Self-supervision based on the information extracted from large knowledge graphs has been shown to improve the generalization of language models, in zero-shot evaluation on various downstream language reasoning tasks. Since these improvements are reported in aggregate, however, little is known about (i) how to select the appropriate knowledge for solid performance across tasks, (ii) how to combine this knowledge with neural language models, and (iii) how these pairings affect granular task performance. In this paper, we study the effect of knowledge sampling strategies and sizes that can be used to generate synthetic data for adapting language models. We study the effect of different synthetic datasets on language models with various architectures and sizes. The resulting models are evaluated against four task properties: domain overlap, answer similarity, vocabulary overlap, and answer length. Our experiments show that encoder-decoder models benefit from more data to learn from, whereas sampling strategies that balance across different aspects yield best performance. Most of the improvement occurs on questions with short answers and dissimilar answer candidates, which corresponds to the characteristics of the data used for pre-training.
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderKnowledge GraphsSimilar Papers 제목 키워드 기반
An Empirical Investigation of Commonsense Self-Supervision with Knowledge Graphs
Large knowledge graphs have been shown to benefit zero-shot evaluation of downstream tasks, through continual pre-training of language models. Yet, little is known about how to optimally learn from this knowledge, and wh…
Knowledge GraphsCommonsense Knowledge Transfer for Pre-trained Language Models
Despite serving as the foundation models for a wide range of NLP benchmarks, pre-trained language models have shown limited capabilities of acquiring implicit commonsense knowledge from self-supervision alone, compared t…
Language ModelingLanguage ModellingRelation PredictionTransfer LearningCommonsense Knowledge Transfer for Pre-trained Language Models
Despite serving as the foundation models for a wide range of NLP benchmarks, pre-trained language models have shown limited capabilities of acquiring implicit commonsense knowledge from self-supervision alone, compared t…
Language ModelingLanguage ModellingRelation PredictionTransfer LearningA Systematic Investigation of Commonsense Knowledge in Large Language Models
Language models (LMs) trained on large amounts of data have shown impressive performance on many NLP tasks under the zero-shot and few-shot setup. Here we aim to better understand the extent to which such models learn co…
COMET: Commonsense Transformers for Automatic Knowledge Graph Construction
We present the first comprehensive study on automatic knowledge base construction for two prevalent commonsense knowledge graphs: ATOMIC (Sap et al., 2019) and ConceptNet (Speer et al., 2017). Contrary to many convention…
graph constructionKnowledge Base ConstructionKnowledge Graphs