Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs
This work addresses the challenge of summarizing complex human-human conversations for applications like customer service or meeting notes, representing an incremental improvement over existing methods.
The paper tackles the problem of insufficient, redundant, or incorrect content in abstractive conversation summarization by explicitly modeling discourse relations and action triples through structured graphs, resulting in models that outperform state-of-the-art methods and generalize well across domains.
Abstractive conversation summarization has received much attention recently. However, these generated summaries often suffer from insufficient, redundant, or incorrect content, largely due to the unstructured and complex characteristics of human-human interactions. To this end, we propose to explicitly model the rich structures in conversations for more precise and accurate conversation summarization, by first incorporating discourse relations between utterances and action triples ("who-doing-what") in utterances through structured graphs to better encode conversations, and then designing a multi-granularity decoder to generate summaries by combining all levels of information. Experiments show that our proposed models outperform state-of-the-art methods and generalize well in other domains in terms of both automatic evaluations and human judgments. We have publicly released our code at https://github.com/GT-SALT/Structure-Aware-BART.