Variational Inference for Learning Representations of Natural Language Edits
This work addresses the need for better edit representations in document version control and NLP, though it appears incremental as it builds on existing ideas with a novel method.
The paper tackles the problem of learning distributed representations of natural language edits by proposing a variational inference approach to capture semantic information in a continuous latent space, resulting in the introduction of a new evaluation suite called PEER for standardized automatic assessment.
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.