Text segmentation aims to divide text into contiguous, semantically coherent segments, while segment labeling deals with producing labels for each segment. Past work has shown success in tackling segmentation and labeling for documents and conversations. This has been possible with a combination of task-specific pipelines, supervised and unsupervised learning objectives. In this work, we propose a single encoder-decoder neural network that can handle long documents and conversations, trained simultaneously for both segmentation and segment labeling using only standard supervision. We successfully show a way to solve the combined task as a pure generation task, which we refer to as structured summarization. We apply the same technique to both document and conversational data, and we show state of the art performance across datasets for both segmentation and labeling, under both high- and low-resource settings. Our results establish a strong case for considering text segmentation and segment labeling as a whole, and moving towards general-purpose techniques that don't depend on domain expertise or task-specific components.
翻译:文本分割旨在将文字分为毗连、 语义一致的部分, 而区段标签则处理每个区段的标签。 过去的工作显示在处理分割和文档和对话的标签方面取得成功。 这是通过将特定任务管道、 受监管和不受监管的学习目标相结合而实现的。 在这项工作中,我们提议建立一个单一的编码解码神经网络, 该网络可以处理长文件和对话, 仅使用标准监督, 同时培训分解和分段标签。 我们成功地展示了解决混合任务的方法, 将之作为纯代任务, 我们称之为结构化的合成。 我们将同样的技术应用于文档和谈话数据, 我们展示了高资源环境和低资源环境下的分解和标签的跨数据集的艺术性能。 我们的结果为整体考虑文本分割和分段标签, 并转向不依赖域专门知识或特定任务组成部分的通用技术提供了有力的理由。