Variational Inference for Learning Representations of Natural Language Edits

Authors

  • Edison Marrese-Taylor The University of Tokyo
  • Machel Reid The University of Tokyo
  • Yutaka Matsuo The University of Tokyo

DOI:

https://doi.org/10.1609/aaai.v35i15.17598

Keywords:

Applications

Abstract

Document editing has become a pervasive component of 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.

Downloads

Published

2021-05-18

How to Cite

Marrese-Taylor, E., Reid, M., & Matsuo, Y. (2021). Variational Inference for Learning Representations of Natural Language Edits. Proceedings of the AAAI Conference on Artificial Intelligence, 35(15), 13552-13560. https://doi.org/10.1609/aaai.v35i15.17598

Issue

Section

AAAI Technical Track on Speech and Natural Language Processing II