How Does Counterfactually Augmented Data Impact Models for Social Computing Constructs?
arXiv:2109.07022
Abstract
As NLP models are increasingly deployed in socially situated settings such as online abusive content detection, it is crucial to ensure that these models are robust. One way of improving model robustness is to generate counterfactually augmented data (CAD) for training models that can better learn to distinguish between core features and data artifacts. While models trained on this type of data have shown promising out-of-domain generalizability, it is still unclear what the sources of such improvements are. We investigate the benefits of CAD for social NLP models by focusing on three social computing constructs -- sentiment, sexism, and hate speech. Assessing the performance of models trained with and without CAD across different types of datasets, we find that while models trained on CAD show lower in-domain performance, they generalize better out-of-domain. We unpack this apparent discrepancy using machine explanations and find that CAD reduces model reliance on spurious features. Leveraging a novel typology of CAD to analyze their relationship with model performance, we find that CAD which acts on the construct directly or a diverse set of CAD leads to higher performance.
arXiv commentPreprint of a paper accepted to EMNLP 2021
References in corpus (9)
- Scikit-learn: Machine Learning in Python
- Axiomatic Attribution for Deep Networks
- Directions in Abusive Language Training Data: Garbage In, Garbage Out
- Adversarial Filters of Dataset Biases
- Data Poisoning Attack against Unsupervised Node Embedding Methods
- Generate Your Counterfactuals: Towards Controlled Counterfactual Generation for Text
- Global Aggregations of Local Explanations for Black Box models
- A Neighbourhood Framework for Resource-Lean Content Flagging
- "Call me sexist, but...": Revisiting Sexism Detection Using Psychological Scales and Adversarial Samples