Topic-Informed Dialogue Summarization using Topic Distribution and Prompt-based Modeling
Submission Type: Regular Short Paper
Submission Track: Summarization
Submission Track 2: Dialogue and Interactive Systems
Keywords: Dialogue Summarization, Topic Distribution, Topic-Informed Prompt
TL;DR: This paper presents TIDSum, a novel dialogue summarization model that considers topic distribution in the dialogue to generate the summary.
Abstract: Dealing with multiple topics should be considered an important issue in dialogue summarization, because dialogues, unlike documents, are prone to topic drift. Thus, we propose a new dialogue summarization model that reflects dialogue topic distribution to consider all topics present in the dialogue. First, the distribution of dialogue topics is estimated by an effective topic discovery model. Then topic-informed prompt transfers estimated topic distribution information to the output of encoder and decoder vectors. Finally, the topic extractor estimates the summary topic distribution from the output context vector of decoder to distinguish its difference from the dialogue topic distribution. To consider the proportion of each topic distribution appeared in the dialogue, the extractor is trained to reduce the difference between the distributions of the dialogue and the summary. The experimental results on SAMSum and DialogSum show that our model outperforms state-of-the-art methods on ROUGE scores. The human evaluation results also show that our framework well generates comprehensive summaries.
Submission Number: 2758
Loading