Knowledge Graph-Augmented Korean Generative Commonsense Reasoning
This work addresses the problem of improving commonsense reasoning for Korean language applications, but it appears incremental as it builds on existing datasets and methods.
The paper tackles the problem of Korean generative commonsense reasoning by proposing a method that utilizes Korean knowledge graph data to address limitations in language models, such as failing to consider concept relationships and deep knowledge. The result shows enhanced efficiency in Korean commonsense inference, though no concrete numbers are provided.
Generative commonsense reasoning refers to the task of generating acceptable and logical assumptions about everyday situations based on commonsense understanding. By utilizing an existing dataset such as Korean CommonGen, language generation models can learn commonsense reasoning specific to the Korean language. However, language models often fail to consider the relationships between concepts and the deep knowledge inherent to concepts. To address these limitations, we propose a method to utilize the Korean knowledge graph data for text generation. Our experimental result shows that the proposed method can enhance the efficiency of Korean commonsense inference, thereby underlining the significance of employing supplementary data.