CoCoLM: COmplex COmmonsense Enhanced Language Model with Discourse Relations (2012.15643v2)

Abstract: Large-scale pre-trained LLMs have demonstrated strong knowledge representation ability. However, recent studies suggest that even though these giant models contains rich simple commonsense knowledge (e.g., bird can fly and fish can swim.), they often struggle with the complex commonsense knowledge that involves multiple eventualities (verb-centric phrases, e.g., identifying the relationship between Jim yells at Bob'' andBob is upset'').To address this problem, in this paper, we propose to help pre-trained LLMs better incorporate complex commonsense knowledge. Different from existing fine-tuning approaches, we do not focus on a specific task and propose a general LLM named CoCoLM. Through the careful training over a large-scale eventuality knowledge graphs ASER, we successfully teach pre-trained LLMs (i.e., BERT and RoBERTa) rich complex commonsense knowledge among eventualities. Experiments on multiple downstream commonsense tasks that requires the correct understanding of eventualities demonstrate the effectiveness of CoCoLM.