In this work, we test the performance of two bidirectional transformer-based language models, BERT and SpanBERT, on predicting directionality in causal pairs in the textual content. Our preliminary results show that predicting direction for inter-sentence and implicit causal relations is more challenging. And, SpanBERT performs better than BERT on causal samples with longer span length. We also introduce CREST which is a framework for unifying a collection of scattered datasets of causal relations.
@article{arxiv.2103.13606,
title = {Predicting Directionality in Causal Relations in Text},
author = {Pedram Hosseini and David A. Broniatowski and Mona Diab},
journal= {arXiv preprint arXiv:2103.13606},
year = {2021}
}