Publication Details

BUT-FIT at SemEval-2020 Task 5: Automatic detection of counterfactual statements with deep pre-trained language representation models

FAJČÍK Martin, DOČEKAL Martin, JON Josef and SMRŽ Pavel. BUT-FIT at SemEval-2020 Task 5: Automatic detection of counterfactual statements with deep pre-trained language representation models. In: Proceedings of the Fourteenth Workshop on Semantic Evaluation. Barcelona (online): Association for Computational Linguistics, 2020, pp. 437-444. ISBN 978-1-952148-31-6. Available from: https://www.aclweb.org/anthology/2020.semeval-1.53/
Czech title
BUT-FIT na SemEval-2020 Task 5: Automatická detekce kontrafaktuálních výrazů s použitím hlubokých předtrénovaných modelů
Type
conference paper
Language
english
Authors
Fajčík Martin, Ing., Ph.D. (DCGM FIT BUT)
Dočekal Martin, Ing. (DCGM FIT BUT)
Jon Josef, Ing. (DCGM FIT BUT)
Smrž Pavel, doc. RNDr., Ph.D. (DCGM FIT BUT)
URL
Keywords

counterfactual, counterfactual reasoning, BERT, RoBERTa, ALBERT, causal reasoning, what-if, semeval, classification, extraction

Abstract

This paper describes BUT-FITs submission at SemEval-2020 Task 5: Modelling Causal Reasoning in Language: Detecting Counterfactuals. The challenge focused on detecting whether a given statement contains a counterfactual (Subtask 1) and extracting both antecedent and consequent parts of the counterfactual from the text (Subtask 2). We experimented with various state-of-the-art language representation models (LRMs). We found RoBERTa LRM to perform the best in both subtasks. We achieved the first place in both exact match and F1 for Subtask 2 and ranked second for Subtask 1.

Published
2020
Pages
437-444
Proceedings
Proceedings of the Fourteenth Workshop on Semantic Evaluation
Conference
The 28th International Conference on Computational Linguistics, Barcelona (online), ES
ISBN
978-1-952148-31-6
Publisher
Association for Computational Linguistics
Place
Barcelona (online), ES
EID Scopus
2-s2.0-85123298637
BibTeX 
@INPROCEEDINGS{FITPUB12416,
   author = "Martin Faj\v{c}\'{i}k and Martin Do\v{c}ekal and Josef Jon and Pavel Smr\v{z}",
   title = "BUT-FIT at SemEval-2020 Task 5: Automatic detection of counterfactual statements with deep pre-trained language representation models",
   pages = "437--444",
   booktitle = "Proceedings of the Fourteenth Workshop on Semantic Evaluation",
   year = 2020,
   location = "Barcelona (online), ES",
   publisher = "Association for Computational Linguistics",
   ISBN = "978-1-952148-31-6",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/12416"
}
Back to top