Alleviating the Knowledge-Language Inconsistency: A Study for Deep Commonsense Knowledge
This addresses a specific challenge in natural language processing for improving commonsense reasoning in AI systems, but it is incremental as it builds on existing methods for knowledge mining.
The paper tackles the problem of knowledge-language inconsistency in commonsense knowledge, where relational triples are inconsistent with language expression, challenging pre-trained language models; it proposes a novel method to mine deep commonsense knowledge from sentences, significantly improving performance in capturing such knowledge.
Knowledge facts are typically represented by relational triples, while we observe that some commonsense facts are represented by the triples whose forms are inconsistent with the expression of language. This inconsistency puts forward a challenge for pre-trained language models to deal with these commonsense knowledge facts. In this paper, we term such knowledge as deep commonsense knowledge and conduct extensive exploratory experiments on it. We show that deep commonsense knowledge occupies a significant part of commonsense knowledge while conventional methods fail to capture it effectively. We further propose a novel method to mine the deep commonsense knowledge distributed in sentences, alleviating the reliance of conventional methods on the triple representation form of knowledge. Experiments demonstrate that the proposal significantly improves the performance in mining deep commonsense knowledge.