Zobrazeno 1 - 10
of 63
pro vyhledávání: '"Anoop Sarkar"'
Autor:
Shuly Wintner, Anoop Sarkar
Publikováno v:
Computational Linguistics, Vol 28, Iss 3 (2021)
Externí odkaz:
https://doaj.org/article/5e02b78f6c4e42348bdac1d34a4f5d12
Autor:
Anoop Sarkar
Publikováno v:
Computational Linguistics, Vol 37, Iss 4 (2021)
Externí odkaz:
https://doaj.org/article/be28f3e08e4d4cbfa1ec715abd26f2aa
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 5 (2021)
Externí odkaz:
https://doaj.org/article/e6e123cedacd48bfa5c2da8bb87abd30
We propose a novel data-augmentation technique for neural machine translation based on ROT-$k$ ciphertexts. ROT-$k$ is a simple letter substitution cipher that replaces a letter in the plaintext with the $k$th letter after it in the alphabet. We firs
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::284b8a70676ea0a94d7e22127e57973c
Autor:
Anoop Sarkar, Hassan S. Shavarani
Publikováno v:
EACL
Adding linguistic information (syntax or semantics) to neural machine translation (NMT) have mostly focused on using point estimates from pre-trained models. Directly using the capacity of massive pre-trained contextual word embedding models such as
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::333162b0f7de016023568b1cbe58a4c5
Publikováno v:
EACL
While the attention heatmaps produced by neural machine translation (NMT) models seem insightful, there is little evidence that they reflect a model’s true internal reasoning. We provide a measure of faithfulness for NMT based on a variety of stres
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e4059cdb32deb44396564f5eb19431a0
https://doi.org/10.18653/v1/2021.eacl-main.243
https://doi.org/10.18653/v1/2021.eacl-main.243
Publikováno v:
ACL/IJCNLP (Findings)
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dbbc4afc87d4c71208be9e3fdd55ee7f
https://doi.org/10.18653/v1/2021.findings-acl.362
https://doi.org/10.18653/v1/2021.findings-acl.362
Publikováno v:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7b8a19cf7a4515051279ca755592a317
https://doi.org/10.18653/v1/2021.emnlp-main.130
https://doi.org/10.18653/v1/2021.emnlp-main.130
Autor:
Ashkan Alinejad, Anoop Sarkar
Publikováno v:
EMNLP (1)
Directly translating from speech to text using an end-to-end approach is still challenging for many language pairs due to insufficient data. Although pretraining the encoder parameters using the Automatic Speech Recognition (ASR) task improves the re
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ad9457706b79ab1be440de4db1e7a93b
https://doi.org/10.18653/v1/2020.emnlp-main.644
https://doi.org/10.18653/v1/2020.emnlp-main.644
Publikováno v:
Transactions of the Association for Computational Linguistics. 5:501-514
Current word alignment models do not distinguish between different types of alignment links. In this paper, we provide a new probabilistic model for word alignment where word alignments are associated with linguistically motivated alignment types. We
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::825a753cf6cc80e330b45e1a35f3cd42
https://doi.org/10.1162/tacl_a_00076
https://doi.org/10.1162/tacl_a_00076