4 papers
Don't Discard All the Biased Instances: Investigating a Core Assumption in Dataset Bias Mitigation Techniques
Hossein Amirkhani, Mohammad Taher Pilehvar
Existing techniques for mitigating dataset bias often leverage a biased model to identify biased instances. The role of these biased instances is then reduced during the training o…
Ensemble Learning-Based Approach for Improving Generalization Capability of Machine Reading Comprehension Systems
Razieh Baradaran, Hossein Amirkhani
Machine Reading Comprehension (MRC) is an active field in natural language processing with many successful developed models in recent years. Despite their high in-distribution accu…
Zero-Shot Estimation of Base Models' Weights in Ensemble of Machine Reading Comprehension Systems for Robust Generalization
Razieh Baradaran, Hossein Amirkhani
One of the main challenges of the machine reading comprehension (MRC) models is their fragile out-of-domain generalization, which makes these models not properly applicable to real…
A Survey on Machine Reading Comprehension Systems
Razieh Baradaran, Razieh Ghiasi, Hossein Amirkhani
Machine reading comprehension is a challenging task and hot topic in natural language processing. Its goal is to develop systems to answer the questions regarding a given context.…