Transfer Learning for Causal Sentence Detection
Computation and Language
2019-06-21 v2
Abstract
We consider the task of detecting sentences that express causality, as a step towards mining causal relations from texts. To bypass the scarcity of causal instances in relation extraction datasets, we exploit transfer learning, namely ELMO and BERT, using a bidirectional GRU with self-attention (BIGRUATT) as a baseline. We experiment with both generic public relation extraction datasets and a new biomedical causal sentence detection dataset, a subset of which we make publicly available. We find that transfer learning helps only in very small datasets. With larger datasets, BIGRUATT reaches a performance plateau, then larger datasets and transfer learning do not help.
Cite
@article{arxiv.1906.07544,
title = {Transfer Learning for Causal Sentence Detection},
author = {Manolis Kyriakakis and Ion Androutsopoulos and Joan Ginés i Ametllé and Artur Saudabayev},
journal= {arXiv preprint arXiv:1906.07544},
year = {2019}
}
Comments
5 pages, short paper at BioNLP 2019 workshop