Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP

Zhijing Jin, Julius von Kügelgen, Jingwei Ni, Tejas Vaidhya, Ayush Kaushal, Mrinmaya Sachan, Bernhard Schoelkopf


Abstract
The principle of independent causal mechanisms (ICM) states that generative processes of real world data consist of independent modules which do not influence or inform each other. While this idea has led to fruitful developments in the field of causal inference, it is not widely-known in the NLP community. In this work, we argue that the causal direction of the data collection process bears nontrivial implications that can explain a number of published NLP findings, such as differences in semi-supervised learning (SSL) and domain adaptation (DA) performance across different settings. We categorize common NLP tasks according to their causal direction and empirically assay the validity of the ICM principle for text data using minimum description length. We conduct an extensive meta-analysis of over 100 published SSL and 30 DA studies, and find that the results are consistent with our expectations based on causal insights. This work presents the first attempt to analyze the ICM principle in NLP, and provides constructive suggestions for future modeling choices.
Anthology ID:
2021.emnlp-main.748
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9499–9513
Language:
URL:
https://aclanthology.org/2021.emnlp-main.748
DOI:
10.18653/v1/2021.emnlp-main.748
Bibkey:
Cite (ACL):
Zhijing Jin, Julius von Kügelgen, Jingwei Ni, Tejas Vaidhya, Ayush Kaushal, Mrinmaya Sachan, and Bernhard Schoelkopf. 2021. Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9499–9513, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP (Jin et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.748.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.748.mp4
Code
 zhijing-jin/icm4nlp