Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents
Authors:
- Yusen ZhangYZYusen Zhang
- Ansong NiANAnsong Ni
- Chenguang ZhuCZChenguang Zhu
- Budhaditya DebBDBudhaditya Deb
- Ahmed H. AwadallahAAAhmed H. Awadallah
- Dragomir RadevDRDragomir Radev
- Rui ZhangRZRui Zhang
Preprint
Abstract
Text summarization helps readers capture salient information from documents, news, interviews, and meetings. However, most state-of-the-art pretrained language models (LM) are unable to efficiently process long text for many summarization tasks. In this paper, we propose Summ$^N$, a simple, flexible, and effective multi-stage framework for input texts that are longer than the maximum context length of typical pretrained LMs. Summ$^N$ first splits the data samples and generates a coarse summary in multiple stages and then produces the final fine-grained summary based on it. Our framework can process input text of arbitrary length by adjusting the number of stages while keeping the LM input size fixed. Moreover, it can deal with both single-source documents and dialogues, and it can be used on top of different backbone abstractive summarization models. To the best of our knowledge, Summ$^N$ is the first multi-stage split-then-summarize framework for long input summarization. Our experiments demonstrate that Summ$^N$ outperforms previous state-of-the-art methods by improving ROUGE scores on three long meeting summarization datasets AMI, ICSI, and QMSum, two long TV series datasets from SummScreen, and a long document summarization dataset GovReport. Our data and code are available at https://github.com/psunlpgroup/Summ-N.Keywords
All Related Versions
This publication has 23 references indexed in Scilit:
- An Exploratory Study on Long Dialogue Summarization: What Works and What’s Next2021
- SummerTime: Text Summarization Toolkit for Non-experts2021
- SummVis: Interactive Visual Analysis of Models, Data, and Evaluation for Text Summarization2021
- ConvoSumm: Conversation Summarization Benchmark and Improved Abstractive Summarization with Argument Mining2021
- Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs2021
- A Hierarchical Network for Abstractive Meeting Summarization with Cross-Domain Pretraining2020
- On Extractive and Abstractive Neural Document Summarization with Transformer Language Models2020
- Coarse-to-Fine Query Focused Multi-Document Summarization2020
- A Divide-and-Conquer Approach to the Summarization of Long DocumentsIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2020
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension2020