Synthetic Propaganda Embeddings To Train A Linear Projection

Adam Ek, Mehdi Ghanimifard


Abstract
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.
Anthology ID:
D19-5023
Volume:
Proceedings of the Second Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Anna Feldman, Giovanni Da San Martino, Alberto Barrón-Cedeño, Chris Brew, Chris Leberknight, Preslav Nakov
Venue:
NLP4IF
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
155–161
Language:
URL:
https://aclanthology.org/D19-5023
DOI:
10.18653/v1/D19-5023
Bibkey:
Cite (ACL):
Adam Ek and Mehdi Ghanimifard. 2019. Synthetic Propaganda Embeddings To Train A Linear Projection. In Proceedings of the Second Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda, pages 155–161, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Synthetic Propaganda Embeddings To Train A Linear Projection (Ek & Ghanimifard, NLP4IF 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/D19-5023.pdf