Semantically Enhanced Models for Commonsense Knowledge Acquisition
This work addresses the challenge of automating commonsense knowledge acquisition for intelligent systems, but it appears incremental as it builds on existing knowledge graph embedding methods.
The paper tackled the problem of acquiring commonsense knowledge, which is often implicit and ambiguous, by proposing semantically enhanced models within a knowledge graph embedding framework to resolve ambiguity and improve reasoning. The results demonstrate the effectiveness of these models in commonsense reasoning, though no concrete numbers are provided.
Commonsense knowledge is paramount to enable intelligent systems. Typically, it is characterized as being implicit and ambiguous, hindering thereby the automation of its acquisition. To address these challenges, this paper presents semantically enhanced models to enable reasoning through resolving part of commonsense ambiguity. The proposed models enhance in a knowledge graph embedding (KGE) framework for knowledge base completion. Experimental results show the effectiveness of the new semantic models in commonsense reasoning.