TTUI at SemEval-2020 Task 11: Propaganda Detection with Transfer learning and Ensembles

Moonsung Kim, Steven Bethard

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Scopus citations

Abstract

In this paper, we describe our approaches and systems for the SemEval-2020 Task 11 on propaganda technique detection. We fine-tuned BERT and RoBERTa pre-trained models then merged them with an average ensemble. We conducted several experiments for input representations dealing with long texts and preserving context as well as for the imbalanced class problem. Our system ranked 20th out of 36 teams with 0.398 F1 in the SI task and 14th out of 31 teams with 0.556 F1 in the TC task. Our code is available at https://github.com/amenra99/SemEval2020_Task11.

Original languageEnglish (US)
Title of host publication14th International Workshops on Semantic Evaluation, SemEval 2020 - co-located 28th International Conference on Computational Linguistics, COLING 2020, Proceedings
EditorsAurelie Herbelot, Xiaodan Zhu, Alexis Palmer, Nathan Schneider, Jonathan May, Ekaterina Shutova
PublisherInternational Committee for Computational Linguistics
Pages1829-1834
Number of pages6
ISBN (Electronic)9781952148316
DOIs
StatePublished - 2020
Event14th International Workshops on Semantic Evaluation, SemEval 2020 - Barcelona, Spain
Duration: Dec 12 2020Dec 13 2020

Publication series

Name14th International Workshops on Semantic Evaluation, SemEval 2020 - co-located 28th International Conference on Computational Linguistics, COLING 2020, Proceedings

Conference

Conference14th International Workshops on Semantic Evaluation, SemEval 2020
Country/TerritorySpain
CityBarcelona
Period12/12/2012/13/20

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computational Theory and Mathematics
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'TTUI at SemEval-2020 Task 11: Propaganda Detection with Transfer learning and Ensembles'. Together they form a unique fingerprint.

Cite this