Generate Your Counterfactuals: Towards Controlled Counterfactual Generation for Text

Abstract

Machine Learning has seen tremendous growth recently, which has led to larger adoption of ML systems for educational assessments, credit risk, healthcare, employment, criminal justice, to name a few. The trustworthiness of ML and NLP systems is a crucial aspect and requires a guarantee that the decisions they make are fair and robust. Aligned with this, we propose a framework GYC, to generate a set of counterfactual text samples, which are crucial for testing these ML systems. Our main contributions include a) We introduce GYC, a framework to generate counterfactual samples such that the generation is plausible, diverse, goal-oriented, and effective, b) We generate counterfactual samples, that can direct the generation towards a corresponding condition such as named-entity tag, semantic role label, or sentiment. Our experimental results on various domains show that GYC generates counterfactual text samples exhibiting the above four properties. GYC generates counterfactuals that can act as test cases to evaluate a model and any text debiasing algorithm.

Accepted at AAAI Conference on Artificial Intelligence (AAAI 2021)

Cited by in corpus (5)

• Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models
• Interventional Aspect-Based Sentiment Analysis
• Transferable Persona-Grounded Dialogues via Grounded Minimal Edits
• How Does Counterfactually Augmented Data Impact Models for Social Computing Constructs?
• $C^3$: Compositional Counterfactual Contrastive Learning for Video-grounded Dialogues