Udeepa Meepegama

2 accepted papers

2022

Generative Pretraining for Paraphrase Evaluation

Jack Weston, Raphael Lenain, Udeepa Meepegama, Emil Fristed

ACL 2022long

We introduce ParaBLEU, a paraphrase representation learning model and evaluation metric for text generation. Unlike previous approaches, ParaBLEU learns to understand paraphrasis using generative conditioning as a pretraining objective. ParaBLEU correlates more strongly with human judgements than ex…

Cited by 15 Source ↗PDF ↗Scholar ↗

2021

Learning de-identified representations of prosody from raw audio

Jack Weston, Raphael Lenain, Udeepa Meepegama, Emil Fristed

ICML 2021spotlight

We propose a method for learning de-identified prosody representations from raw audio using a contrastive self-supervised signal. Whereas prior work has relied on conditioning models with bottlenecks, we introduce a set of inductive biases that exploit the natural structure of prosody to minimize ti…

Cited by 29 Source ↗PDF ↗Scholar ↗