paper

Vec2Sent: Probing Sentence Embeddings with Natural Language Generation

arXiv:2011.00592

Abstract

We introspect black-box sentence embeddings by conditionally generating from them with the objective to retrieve the underlying discrete sentence. We perceive of this as a new unsupervised probing task and show that it correlates well with downstream task performance. We also illustrate how the language generated from different encoders differs. We apply our approach to generate sentence analogies from sentence embeddings.

Accepted for publication in COLING 2020

References in corpus (4)