DCN+: Mixed Objective and Deep Residual Coattention for Question Answering

Caiming XiongVictor ZhongRichard Socher

   Papers with code   Abstract  PDF

Traditional models for question answering optimize using cross entropy loss, which encourages exact answers at the cost of penalizing nearby or overlapping answers that are sometimes equally accurate. We propose a mixed objective that combines cross entropy loss with self-critical policy learning... (read more)

Benchmarked Models

No benchmarked models yet. Click here to submit a model.