Dial2Desc: End-to-end Dialogue Description Generation
This addresses the problem of efficiently summarizing dialogues for users who need to quickly grasp conversation topics, though it is incremental as it builds on existing dialogue summarization tasks.
The authors introduced a new task called Dialogue Description (Dial2Desc) to generate concise descriptions of objects or actions from dialogues, enabling quick topic extraction without reading the full conversation. They built a dataset with over 100,000 dialogue-description pairs and showed that a neural attentive model outperforms baselines in accuracy and descriptiveness.
We first propose a new task named Dialogue Description (Dial2Desc). Unlike other existing dialogue summarization tasks such as meeting summarization, we do not maintain the natural flow of a conversation but describe an object or an action of what people are talking about. The Dial2Desc system takes a dialogue text as input, then outputs a concise description of the object or the action involved in this conversation. After reading this short description, one can quickly extract the main topic of a conversation and build a clear picture in his mind, without reading or listening to the whole conversation. Based on the existing dialogue dataset, we build a new dataset, which has more than one hundred thousand dialogue-description pairs. As a step forward, we demonstrate that one can get more accurate and descriptive results using a new neural attentive model that exploits the interaction between utterances from different speakers, compared with other baselines.