Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Nishant Kambhatla"'
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
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:
NGT@EMNLP-IJCNLP
Attention models have become a crucial component in neural machine translation (NMT). They are often implicitly or explicitly used to justify the model's decision in generating a specific token but it has not yet been rigorously established to what e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::41b456552a50e0ea3d1435b5ff14b32f
http://arxiv.org/abs/1910.00139
http://arxiv.org/abs/1910.00139
Publikováno v:
LaTeCH@NAACL-HLT
We describe a first attempt at using techniques from computational linguistics to analyze the undeciphered proto-Elamite script. Using hierarchical clustering, n-gram frequencies, and LDA topic models, we both replicate results obtained by manual dec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cd0a0bd4cba8ed59a784b4545d2a6d39
https://doi.org/10.18653/v1/w19-2516
https://doi.org/10.18653/v1/w19-2516
Publikováno v:
EMNLP
Decipherment of homophonic substitution ciphers using language models is a well-studied task in NLP. Previous work in this topic scores short local spans of possible plaintext decipherments using n-gram language models. The most widely used technique
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0a044d9e06605e06219e914d809b5bc5
https://doi.org/10.18653/v1/d18-1102
https://doi.org/10.18653/v1/d18-1102
Publikováno v:
ALW
Automated filters are commonly used by online services to stop users from sending age-inappropriate, bullying messages, or asking others to expose personal information. Previous work has focused on rules or classifiers to detect and filter offensive
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e5a5858f5846a5c3d0d7a8218d4e55e4
https://doi.org/10.18653/v1/w18-5119
https://doi.org/10.18653/v1/w18-5119