Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Dana Ruiter"'
Recent research on style transfer takes inspiration from unsupervised neural machine translation (UNMT), learning from large amounts of non-parallel data by exploiting cycle consistency loss, back-translation, and denoising autoencoders. By contrast,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::08695c2ac546f824a2287cb5021f3f0a
Publikováno v:
Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021).
Hate speech and profanity detection suffer from data sparsity, especially for languages other than English, due to the subjective nature of the tasks and the resulting annotation incompatibility of existing corpora. In this study, we identify profane
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e2d577165cbc56332d23318365823623
https://doi.org/10.18653/v1/2021.woah-1.2
https://doi.org/10.18653/v1/2021.woah-1.2
Publikováno v:
EACL (Student Research Workshop)
Sentiment tasks such as hate speech detection and sentiment analysis, especially when performed on languages other than English, are often low-resource. In this study, we exploit the emotional information encoded in emojis to enhance the performance
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::aad74a1601a308f29e1eadb900d10f0b
https://doi.org/10.18653/v1/2021.eacl-srw.15
https://doi.org/10.18653/v1/2021.eacl-srw.15
Publikováno v:
Text, Speech, and Dialogue ISBN: 9783030835262
TDS
TDS
Deep Neural Network (DNN) based classifiers have gained increased attention in hate speech classification. However, the performance of DNN classifiers increases with quantity of available training data and in reality, hate speech datasets consist of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fc7e000254a2e0a138b3697c711ab084
https://doi.org/10.1007/978-3-030-83527-9_12
https://doi.org/10.1007/978-3-030-83527-9_12
Autor:
Moritz Wolf, Dana Ruiter, Dietrich Klakow, Jan Alexandersson, Ashwin Geet D'Sa, Liane Reiners
Publikováno v:
EMNLP 2020 System Demonstration
EMNLP 2020 System Demonstration, Nov 2020, Punta Cana (Virtual), Dominican Republic
EMNLP (Demos)
EMNLP 2020 System Demonstration, Nov 2020, Punta Cana (Virtual), Dominican Republic
EMNLP (Demos)
A lot of real-world phenomena are complex and cannot be captured by single task annotations. This causes a need for subsequent annotations, with interdependent questions and answers describing the nature of the subject at hand. Even in the case a phe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e8a27416733b65e9d346646964eac189
https://hal.inria.fr/hal-02958831
https://hal.inria.fr/hal-02958831
Publikováno v:
Insights
Insights from Negative Results Workshop, EMNLP 2020
Insights from Negative Results Workshop, EMNLP 2020, Nov 2020, Punta Cana, Dominican Republic
Insights from Negative Results Workshop, EMNLP 2020
Insights from Negative Results Workshop, EMNLP 2020, Nov 2020, Punta Cana, Dominican Republic
International audience; Research on hate speech classification has received increased attention. In real-life scenarios , a small amount of labeled hate speech data is available to train a reliable classifier. Semi-supervised learning takes advantage
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d1e8d5039978be5668b46c98defb2b73
https://doi.org/10.18653/v1/2020.insights-1.8
https://doi.org/10.18653/v1/2020.insights-1.8
Publikováno v:
EMNLP (1)
Self-supervised neural machine translation (SSNMT) jointly learns to identify and select suitable training data from comparable (rather than parallel) corpora and to translate, in a way that the two tasks support each other in a virtuous circle. In t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5fe9db7a79ef0cc33a6bb154fd25f0d3
Publikováno v:
ACL (1)
We present a simple new method where an emergent NMT system is used for simultaneously selecting training data and learning internal NMT representations. This is done in a self-supervised way without parallel data, in such a way that both tasks enhan
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::af6debab4fb60e970edaaf05332785aa
https://doi.org/10.18653/v1/p19-1178
https://doi.org/10.18653/v1/p19-1178