Zobrazeno 1 - 10
of 385
pro vyhledávání: '"A, Kleinbauer"'
Transferring knowledge from one domain to another is of practical importance for many tasks in natural language processing, especially when the amount of available data in the target domain is limited. In this work, we propose a novel few-shot approa
Externí odkaz:
http://arxiv.org/abs/2206.07841
Autor:
Ruiter, Dana, Kleinbauer, Thomas, España-Bonet, Cristina, van Genabith, Josef, Klakow, Dietrich
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:
http://arxiv.org/abs/2205.08814
Autor:
Ruiter, Dana, Reiners, Liane, D'Sa, Ashwin Geet, Kleinbauer, Thomas, Fohr, Dominique, Illina, Irina, Klakow, Dietrich, Schemer, Christian, Monnier, Angeliki
Even though hate speech (HS) online has been an important object of research in the last decade, most HS-related corpora over-simplify the phenomenon of hate by attempting to label user comments as "hate" or "neutral". This ignores the complex and su
Externí odkaz:
http://arxiv.org/abs/2204.13400
Autor:
Adelani, David Ifeoluwa, Zhang, Miaoran, Shen, Xiaoyu, Davody, Ali, Kleinbauer, Thomas, Klakow, Dietrich
Documents as short as a single sentence may inadvertently reveal sensitive information about their authors, including e.g. their gender or ethnicity. Style transfer is an effective way of transforming texts in order to remove any information that ena
Externí odkaz:
http://arxiv.org/abs/2109.09133
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:
http://arxiv.org/abs/2106.07505
Machine Learning approaches to Natural Language Processing tasks benefit from a comprehensive collection of real-life user data. At the same time, there is a clear need for protecting the privacy of the users whose data is collected and processed. Fo
Externí odkaz:
http://arxiv.org/abs/2008.03101
Differentially private stochastic gradient descent (DPSGD) is a variation of stochastic gradient descent based on the Differential Privacy (DP) paradigm, which can mitigate privacy threats that arise from the presence of sensitive information in trai
Externí odkaz:
http://arxiv.org/abs/2006.10919
Autor:
Anne Kleinbauer, Felix Pankonin
Publikováno v:
Totalitarismus und Demokratie, Vol 18, Iss 2, Pp 285-296 (2021)
The MAZEWA project is presented here as an example of the work of the Netzwerkstatt of Hillersche Villa in Zittau which aims to further develop the remembrance and commemoration work around the local Jewish cemetery. Using Heritage Interpretati
Externí odkaz:
https://doaj.org/article/b5dd03de670a4908a8200a6050296a4f
Publikováno v:
In Discrete Applied Mathematics 30 September 2019 269:32-40
Publikováno v:
Diversity and Distributions, 2018 May 01. 24(5/6), 652-665.
Externí odkaz:
https://www.jstor.org/stable/44896987