Counterfactual Inference

AbstractToday’s text classifiers inevitably suffer from unintended dataset biases, especially the document-level label bias and word-level keyword bias, which may hurt models’ generalization. Many previous studies employed data-level manipulations or …...

AbstractThe construction of open-domain dialogue systems requires high-quality dialogue datasets. The dialogue data admits a wide variety of responses for a given dialogue history, especially responses with different semantics. However, …...

AbstractAnalogy-making gives rise to reasoning, abstraction, flexible categorization and counterfactual inference – abilities lacking in even the best AI systems today. Much research has suggested that analogies are key to …...

AbstractDespite their promising results on standard benchmarks, NLU models are still prone to make predictions based on shortcuts caused by unintended bias in the dataset. For example, an NLI model …...