ECNU-SenseMaker at SemEval-2020 Task 4: Leveraging Heterogeneous Knowledge Resources for Commonsense Validation and Explanation
This work addresses the problem of improving machine commonsense understanding for natural language processing tasks, representing an incremental advance with a novel hybrid method.
The paper tackled commonsense validation and explanation by proposing a Knowledge-enhanced Graph Attention Network (KEGAT) that leverages heterogeneous knowledge from ConceptNet and unstructured text, achieving state-of-the-art accuracy in the Commonsense Explanation subtask.
This paper describes our system for SemEval-2020 Task 4: Commonsense Validation and Explanation (Wang et al., 2020). We propose a novel Knowledge-enhanced Graph Attention Network (KEGAT) architecture for this task, leveraging heterogeneous knowledge from both the structured knowledge base (i.e. ConceptNet) and unstructured text to better improve the ability of a machine in commonsense understanding. This model has a powerful commonsense inference capability via utilizing suitable commonsense incorporation methods and upgraded data augmentation techniques. Besides, an internal sharing mechanism is cooperated to prohibit our model from insufficient and excessive reasoning for commonsense. As a result, this model performs quite well in both validation and explanation. For instance, it achieves state-of-the-art accuracy in the subtask called Commonsense Explanation (Multi-Choice). We officially name the system as ECNU-SenseMaker. Code is publicly available at https://github.com/ECNU-ICA/ECNU-SenseMaker.