# Domain Adaptative Causality Encoder

arXiv: https://arxiv.org/abs/2011.13549 · HTML: https://mlsanity.com/paper/2011.13549/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2020.

## Built on by (most cited first, 8 of 8)

- [Conditional Extreme Value Theory for Open Set Video Domain Adaptation](https://mlsanity.com/paper/2109.00522/) (2021)
- [Exploring Causal Learning through Graph Neural Networks: An In-depth Review](https://mlsanity.com/paper/2311.14994/) (2023)
- [Enhancing Complex Causality Extraction via Improved Subtask Interaction and Knowledge Fusion](https://mlsanity.com/paper/2408.03079/) (2024)
- [Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data Selection](https://mlsanity.com/paper/2109.04292/) (2021)
- [A Cross-Domain Evaluation of Approaches for Causal Knowledge Extraction](https://mlsanity.com/paper/2308.03891/) (2023)
- [An Empirical Study of Causal Relation Extraction Transfer: Design and Data](https://mlsanity.com/paper/2503.06076/) (2025)
- [Benchmarking LLMs for Pairwise Causal Discovery in Biomedical and Multi-Domain Contexts](https://mlsanity.com/paper/2601.15479/) (2026)
- [PubMedCausal: A Span-Level Annotated Corpus for Causal Relation Extraction in Biomedical Text](https://mlsanity.com/paper/2605.28363/) (2026)

## Abstract (arXiv)

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.