To the top

Page Manager: Webmaster
Last update: 9/11/2012 3:13 PM

Tell a friend about this page
Print version

Synthetic Propaganda Embe… - University of Gothenburg, Sweden Till startsida
To content Read more about how we use cookies on

Synthetic Propaganda Embeddings to Train a Linear Projection

Conference paper
Authors Adam Ek
Mehdi Ghanimifard
Published in Proceedings of The 2nd Workshop on NLP for Internet Freedom
Publisher Association for Computational Linguistics
Place of publication Hong Kong
Publication year 2019
Published at Department of Philosophy, Linguistics and Theory of Science
Language en
Keywords transfer learning, neural language modeling, contextual embeddings, propaganda detection
Subject categories Language Technology (Computational Linguistics), Computational linguistics


This paper presents a method of detecting fine-grained categories of propaganda in text. Given a sentence, our method aims to identify a span of words and predict the type of propaganda used. To detect propaganda, we explore a method for extracting features of propaganda from contextualized embeddings without fine-tuning the large parameters of the base model. We show that by generating synthetic embeddings we can train a linear function with ReLU activation to extract useful labeled embeddings from an embedding space generated by a general-purpose language model. We also introduce an inference technique to detect continuous spans in sequences of propaganda tokens in sentences. A result of the ensemble model is submitted to the first shared task in fine-grained propaganda detection at NLP4IF as Team Stalin. In this paper, we provide additional analysis regarding our method of detecting spans of propaganda with synthetically generated representations.

Page Manager: Webmaster|Last update: 9/11/2012

The University of Gothenburg uses cookies to provide you with the best possible user experience. By continuing on this website, you approve of our use of cookies.  What are cookies?