output
20142024
most citedBootstrap your own latent: A new approach to self-supervised Learning

3.4k citations

Showing cs.CLShow all

5 papers · 1 filter

cs.CL20212 cited

Multi-view Subword Regularization

Xinyi Wang, Sebastian Ruder, Graham Neubig

Multilingual pretrained representations generally rely on subword segmentation algorithms to create a shared multilingual vocabulary. However, standard heuristic algorithms often l…

cs.CL202112 cited

Decoupling the Role of Data, Attention, and Losses in Multimodal Transformers

Lisa Anne Hendricks, John Mellor, Rosalia Schneider +2

Recently multimodal transformer models have gained popularity because their performance on language and vision tasks suggest they learn rich visual-linguistic representations. Focu…

cs.CL2020

Improving Adversarial Text Generation by Modeling the Distant Future

Ruiyi Zhang, Changyou Chen, Zhe Gan +5

Auto-regressive text generation models usually focus on local fluency, and may cause inconsistent semantic meaning in long text generation. Further, automatically generating words…

cs.CL20201 cited

Nested-Wasserstein Self-Imitation Learning for Sequence Generation

Ruiyi Zhang, Changyou Chen, Zhe Gan +3

Reinforcement learning (RL) has been widely studied for improving sequence-generation models. However, the conventional rewards used for RL training typically cannot capture suffic…

cs.CL2016116 cited

Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation

Alexandre Berard, Olivier Pietquin, Christophe Servan +1

This paper proposes a first attempt to build an end-to-end speech-to-text translation system, which does not use source language transcription during learning or decoding. We propo…