Transfer Learning for Causal Sentence Detection

2019/06/18 by Kyriakakis, Manolis, Androutsopoulos, Ion, Ametllé, Joan Ginés i +1 · 1 citation
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.1906.07544

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.

Cited by

• A Multi-Level Benchmark for Causal Language Understanding in Social Media Discourse

Related

• An Empirical Study of Causal Relation Extraction Transfer: Design and Data
• Causal BERT : Language models for causality detection between events expressed in text
• A Survey on Extraction of Causal Relations from Natural Language Text
• Automatic Extraction of Causal Relations from Natural Language Texts: A Comprehensive Survey
• Probing Causality Manipulation of Large Language Models