Search Results for author:
Found 11 papers, 7 papers with code
TOKEN is a MASK: Few-shot Named Entity Recognition with Pre-trained Language Models
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.
Exploiting Social Media Content for Self-Supervised Style Transfer
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.
Placing M-Phasis on the Plurality of Hate: A Feature-Based Corpus of Hate Online
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".
Preventing Author Profiling through Zero-Shot Multilingual Back-Translation
Documents as short as a single sentence may inadvertently reveal sensitive information about their authors, including e. g. their gender or ethnicity.
Modeling Profanity and Hate Speech in Social Media with Semantic Subspaces
We observe that, on both similar and distant target tasks and across all languages, the subspace-based representations transfer more effectively than standard BERT representations in the zero-shot setting, with improvements between F1 +10. 9 and F1 +42. 9 over the baselines across all tested monolingual and cross-lingual scenarios.
Privacy Guarantees for De-identifying Text Transformations
Machine Learning approaches to Natural Language Processing tasks benefit from a comprehensive collection of real-life user data.
On the effect of normalization layers on Differentially Private training of deep Neural networks
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 training data.
