Domain adaptative causality encoder

Farhad Moghimifar, Reza Haffari, Mahsa Baktashmotlagh

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearch


Automated discovery of causal relationships from text is a challenging task. Current approaches which are mainly based on the extraction of low-level relations among individual events are limited by the shortage of publicly available labelled data. Therefore, the resulting models perform poorly when applied to a distributionally different domain for which labelled data did not exist at the time of training. To overcome this limitation, in this paper, we leverage the characteristics of dependency trees and adversarial learning to address the tasks of adaptive causality identification and localisation. The term adaptive is used since the training and test data come from two distributionally different datasets, which to the best of our knowledge, this work is the first to address. Moreover, we present a new causality dataset, namely MedCaus, which integrates all types of causality in the text. Our experiments on four different benchmark causality datasets demonstrate the superiority of our approach over the existing baselines, by up to 7% improvement, on the tasks of identification and localisation of the causal relations from the text.
Original languageEnglish
Title of host publicationALTA 2020
Subtitle of host publicationProceedings of the 18th Workshop of the Australasian Language Technology Association
EditorsMaria Kim, Daniel Beck
Place of PublicationStroudsburg PA USA
PublisherAssociation for Computational Linguistics (ACL)
Number of pages10
Publication statusPublished - 2020
EventAustralasian Language Technology Association Workshop 2020 - Virtual, Australia
Duration: 14 Jan 202115 Jan 2021
Conference number: 18th (Website) (Proceedings)


ConferenceAustralasian Language Technology Association Workshop 2020
Abbreviated titleALTA 2020
Internet address

Cite this