Action-Item-Driven Summarization of Long Meeting Transcripts
Action-Item-Driven Summarization of Long Meeting Transcripts
复制标题
DOI：
10.1145/3639233.3639253
复制
发表时间：
2023-12
期刊：
影响因子：
--
通讯作者：
Logan Golia;Jugal Kalita
中科院分区：
文献类型：
--
作者：
Logan Golia;Jugal Kalita
在线会议的日益普及大大增强了能够自动生成给定会议摘要的模型的实用性。本文介绍了一种新颖有效的会议摘要自动生成方法。目前处理这一问题的方法产生一般性和基本的总结，将会议简单地视为一个长对话。然而，我们的新算法可以生成抽象的会议摘要，这些摘要是由会议记录中包含的操作项驱动的。这是通过递归地生成摘要并并行地为会议的每个部分使用我们的动作项提取算法来完成的。然后将所有这些分段总结组合并总结在一起，以创建一个连贯的、行动项目驱动的总结。此外，本文还介绍了三种将长文本划分为基于主题的部分的新方法，以提高算法的时间效率，并解决大型语言模型（llm）忘记长期依赖关系的问题。我们的管道在AMI语料库中实现了64.98的BERTScore，这比目前由微调的BART（双向和自回归变压器）模型产生的最先进的结果提高了约4.98%
The increased prevalence of online meetings has significantly enhanced the practicality of a model that can automatically generate the summary of a given meeting. This paper introduces a novel and effective approach to automate the generation of meeting summaries. Current approaches to this problem generate general and basic summaries, considering the meeting simply as a long dialogue. However, our novel algorithms can generate abstractive meeting summaries that are driven by the action items contained in the meeting transcript. This is done by recursively generating summaries and employing our action-item extraction algorithm for each section of the meeting in parallel. All of these sectional summaries are then combined and summarized together to create a coherent and action-item-driven summary. In addition, this paper introduces three novel methods for dividing up long transcripts into topic-based sections to improve the time efficiency of our algorithm, as well as to resolve the issue of large language models (LLMs) forgetting long-term dependencies. Our pipeline achieved a BERTScore of 64.98 across the AMI corpus, which is an approximately 4.98% increase from the current state-of-the-art result produced by a fine-tuned BART (Bidirectional and Auto-Regressive Transformers) model.1