Disentangling Latent Representations for Interpretability and Controllability

1 Jun 2024

Author:

(1) Mingda Chen.

CHAPTER 5 - DISENTANGLING LATENT REPRESENTATIONS FOR INTERPRETABILITY AND CONTROLLABILITY

In this chapter, we describe our contributions to disentangling latent representations using naturally-occurring structures of paired data. In Section 5.1, we presented a multi-task, latent-variable model that disentangles semantics and syntax in sentence representations. The model leverages the fact that the semantics of a paraphrase pair is shared but syntax varies. In Section 5.2, we extend this framework for controlling the syntax of generated text. In this controlled generation setting, we propose to use a sentential exemplar to control the syntax.

The material in this chapter is adapted from Chen et al. (2019d) and Chen et al. (2019c).

This paper is available on arxiv under CC 4.0 license.