论文标题
自然语言编辑的学习表征的变异推断
Variational Inference for Learning Representations of Natural Language Edits
论文作者
论文摘要
文档编辑已成为信息生产的普遍组成部分，版本控制系统可以有效地存储和应用编辑。鉴于此，最近已经提出了学习编辑分布式表示的任务。考虑到这一点，我们提出了一种新颖的方法，该方法采用各种推理来学习矢量表示的连续潜在空间，以捕获有关文档编辑过程的基本语义信息。我们通过引入潜在变量来明确建模上述功能来实现这一目标。然后将此潜在变量与文档表示形式相结合，以指导该文档的编辑版本的生成。此外，为了促进对编辑表示形式的标准化自动评估，到目前为止，它密切依赖于人类的直接投入，我们还提出了一套下游任务，PEER，专门设计，旨在在自然语言处理的背景下衡量编辑表示的质量。
Document editing has become a pervasive component of the production of information, with version control systems enabling edits to be efficiently stored and applied. In light of this, the task of learning distributed representations of edits has been recently proposed. With this in mind, we propose a novel approach that employs variational inference to learn a continuous latent space of vector representations to capture the underlying semantic information with regard to the document editing process. We achieve this by introducing a latent variable to explicitly model the aforementioned features. This latent variable is then combined with a document representation to guide the generation of an edited version of this document. Additionally, to facilitate standardized automatic evaluation of edit representations, which has heavily relied on direct human input thus far, we also propose a suite of downstream tasks, PEER, specifically designed to measure the quality of edit representations in the context of natural language processing.
