A Hierarchical Network for Abstractive Meeting Summarization with Cross-Domain Pretraining
arXiv:2004.02016
Abstract
With the abundance of automatic meeting transcripts, meeting summarization is of great interest to both participants and other parties. Traditional methods of summarizing meetings depend on complex multi-step pipelines that make joint optimization intractable. Meanwhile, there are a handful of deep neural models for text summarization and dialogue systems. However, the semantic structure and styles of meeting transcripts are quite different from articles and conversations. In this paper, we propose a novel abstractive summary network that adapts to the meeting scenario. We design a hierarchical structure to accommodate long meeting transcripts and a role vector to depict the difference among speakers. Furthermore, due to the inadequacy of meeting summary data, we pretrain the model on large-scale news summary data. Empirical results show that our model outperforms previous approaches in both automatic metrics and human evaluation. For example, on ICSI dataset, the ROUGE-1 score increases from 34.66% to 46.28%.
arXiv commentAccepted in Empirical Methods in Natural Language Processing (EMNLP), 2020
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- Sequence to Sequence Learning with Neural Networks
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
- Teaching Machines to Read and Comprehend
- A Deep Reinforced Model for Abstractive Summarization
- A Hierarchical Neural Autoencoder for Paragraphs and Documents
- Unsupervised Abstractive Meeting Summarization with Multi-Sentence Compression and Budgeted Submodular Maximization
- Leveraging Lead Bias for Zero-shot Abstractive News Summarization
- Topic-aware Pointer-Generator Networks for Summarizing Spoken Conversations