基于摘要提取的Gist检测器增强长文本理解
Enhance Long Text Understanding via Distilled Gist Detector from Abstractive Summarization
摘要：
长文本理解在自然语言处理中是一个重要而又具有挑战性的问题。一篇长文章通常包含许多与主旨无关的多余的词，有时可以被视为噪音。在本文中，我们考虑的问题，如何解开gist-relevant和无关信息的长文本理解。通过提取机制，我们将关于如何从抽象摘要模型中聚焦显著部分的知识转移到提取模型中，并进一步将提取模型（\emph{Gist Detector}）作为补充组件集成到现有模型中，以增强长文本理解。在文档分类、远距离监督开放域问答（DS-QA）和非并行文本风格迁移上的实验表明，该方法能够显著提高基线模型的性能，并取得了最先进的文档分类整体效果。
英文摘要：
Long text understanding is important yet challenging in natural language processing. A long article or essay usually contains many redundant words that are not pertinent to its gist and sometimes can be regarded as noise. In this paper, we consider the problem of how to disentangle the gist-relevant and irrelevant information for long text understanding. With distillation mechanism, we transfer the knowledge about how to focus the salient parts from the abstractive summarization model and further integrate the distilled model, named \emph{Gist Detector}, into existing models as a supplementary component to augment the long text understanding. Experiments on document classification, distantly supervised open-domain question answering (DS-QA) and non-parallel text style transfer show that our method can significantly improve the performance of the baseline models, and achieves state-of-the-art overall results for document classification.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
