Mind the Gap! Injecting Commonsense Knowledge for Abstractive Dialogue Summarization
This addresses the challenge of abstractive dialogue summarization for NLP applications, but it is incremental as it builds on prior work with external knowledge.
The authors tackled the problem of summarizing dialogues by injecting commonsense knowledge to improve informativeness and consistency, resulting in a framework that outperforms existing methods.
In this paper, we propose to leverage the unique characteristics of dialogues sharing commonsense knowledge across participants, to resolve the difficulties in summarizing them. We present SICK, a framework that uses commonsense inferences as additional context. Compared to previous work that solely relies on the input dialogue, SICK uses an external knowledge model to generate a rich set of commonsense inferences and selects the most probable one with a similarity-based selection method. Built upon SICK, SICK++ utilizes commonsense as supervision, where the task of generating commonsense inferences is added upon summarizing the dialogue in a multi-task learning setting. Experimental results show that with injected commonsense knowledge, our framework generates more informative and consistent summaries than existing methods.