Transfer Learning for Causal Sentence Detection
Manolis Kyriakakis, Ion Androutsopoulos, Artur Saudabayev, Joan Ginés i Ametllé · 2019
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, BIGRU-ATT reaches a performance plateau, then larger datasets and transfer learning do not help.