DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization

TL;DR

DialogLM is a pre-trained model designed for understanding and summarizing long multi-person dialogues, employing a window-based denoising approach and hybrid sparse attention to outperform existing models across various dialogue tasks.

Contribution

The paper introduces a novel pre-training framework with window-based denoising and hybrid sparse attention for long dialogue understanding and summarization.

Findings

Significantly outperforms state-of-the-art models on multiple dialogue datasets.

Effective in tasks like dialogue summarization, question answering, and topic segmentation.

Demonstrates robustness on long, multi-person conversations.

Abstract

Dialogue is an essential part of human communication and cooperation. Existing research mainly focuses on short dialogue scenarios in a one-on-one fashion. However, multi-person interactions in the real world, such as meetings or interviews, are frequently over a few thousand words. There is still a lack of corresponding research and powerful tools to understand and process such long dialogues. Therefore, in this work, we present a pre-training framework for long dialogue understanding and summarization. Considering the nature of long conversations, we propose a window-based denoising approach for generative pre-training. For a dialogue, it corrupts a window of text with dialogue-inspired noise, and guides the model to reconstruct this window based on the content of the remaining conversation. Furthermore, to process longer input, we augment the model with sparse attention which is combined with conventional attention in a hybrid manner. We conduct extensive experiments on five datasets of long dialogues, covering tasks of dialogue summarization, abstractive question answering and topic segmentation. Experimentally, we show that our pre-trained model DialogLM significantly surpasses the state-of-the-art models across datasets and tasks. Source code and all the pre-trained models are available on our GitHub repository (https://github.com/microsoft/DialogLM).