Zobrazeno 1 - 10
of 262
pro vyhledávání: '"David Grangier"'
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 9, Pp 1460-1474 (2021)
AbstractHuman evaluation of modern high-quality machine translation systems is a difficult problem, and there is increasing evidence that inadequate evaluation procedures can lead to erroneous conclusions. While there has been considerable research o
Externí odkaz:
https://doaj.org/article/40f406ebbb294289a01d49fc645aacb2
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 9, Pp 53-68 (2021)
AbstractSelf-attention has recently been adopted for a wide range of sequence modeling problems. Despite its effectiveness, self-attention suffers from quadratic computation and memory requirements with respect to sequence length. Successful approach
Externí odkaz:
https://doaj.org/article/21cd91f375224260808b3967ff54015d
Publikováno v:
Transactions of the Association for Computational Linguistics. 9:53-68
Self-attention has recently been adopted for a wide range of sequence modeling problems. Despite its effectiveness, self-attention suffers from quadratic compute and memory requirements with respect to sequence length. Successful approaches to reduce
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::13a1f986f2b914077211ab2c9462d358
https://doi.org/10.1162/tacl_a_00353
https://doi.org/10.1162/tacl_a_00353
Publikováno v:
Findings of the Association for Computational Linguistics: ACL 2022.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::094221564e0ea6cce5ab3a8c0cce3c23
https://doi.org/10.18653/v1/2022.findings-acl.263
https://doi.org/10.18653/v1/2022.findings-acl.263
Publikováno v:
ICASSP
We introduce COLA, a self-supervised pre-training approach for learning a general-purpose representation of audio. Our approach is based on contrastive learning: it learns a representation which assigns high similarity to audio segments extracted fro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4502cc79e67fbe6861d81fb2654bbcca
https://doi.org/10.1109/icassp39728.2021.9413528
https://doi.org/10.1109/icassp39728.2021.9413528
Publikováno v:
ICASSP
We propose CHARM, a method for training a single neural network across inconsistent input channels. Our work is motivated by Electroencephalography (EEG), where data collection protocols from different headsets result in varying channel ordering and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2bc885ea513b6c02e9655f4517a40ce3
http://arxiv.org/abs/2010.13694
http://arxiv.org/abs/2010.13694
Publikováno v:
ACL
We propose a sentence-level language model which selects the next sentence in a story from a finite set of fluent alternatives. Since it does not need to model fluency, the sentence-level language model can focus on longer range dependencies, which a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::af4e75356ab3cf6fb3bfb97030c7b0d3
Autor:
David Grangier, Neil Zeghidour
We introduce Wavesplit, an end-to-end source separation system. From a single mixture, the model infers a representation for each source and then estimates each source signal given the inferred representations. The model is trained to jointly perform
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fb36dbad375e9a93cbc914f2c8bd7182
Publikováno v:
EMNLP (1)
The quality of automatic metrics for machine translation has been increasingly called into question, especially for high-quality systems. This paper demonstrates that, while choice of metric is important, the nature of the references is also critical
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c8e477d247686a0fd4218f5a40ba279a
https://doi.org/10.18653/v1/2020.emnlp-main.5
https://doi.org/10.18653/v1/2020.emnlp-main.5
Autor:
David Grangier, Aurko Roy
Publikováno v:
ACL (1)
Paraphrasing exemplifies the ability to abstract semantic content from surface forms. Recent work on automatic paraphrasing is dominated by methods leveraging Machine Translation (MT) as an intermediate step. This contrasts with humans, who can parap
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bc30665ac1a85a8c4ec35045f6ab1480
http://arxiv.org/abs/1905.12752
http://arxiv.org/abs/1905.12752