Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs
arXiv:2104.08400
Abstract
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.
NAACL 2021
References in corpus (7)
- Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
- A Deep Reinforced Model for Abstractive Summarization
- SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization
- Faithful to the Original: Fact Aware Neural Abstractive Summarization
- ReZero is All You Need: Fast Convergence at Large Depth
- Incorporating Commonsense Knowledge into Abstractive Dialogue Summarization via Heterogeneous Graph Networks
- Automatic Summarization of Open-Domain Podcast Episodes