Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation

Understand

Recent studies have revealed a number of pathologies of neural machine translation (NMT) systems.

• Hypotheses explaining these mostly suggest there is something fundamentally wrong with NMT as a model or its training algorithm, maximum likelihood estimation (MLE).
• Most of this evidence was gathered using maximum a posteriori (MAP) decoding, a decision rule aimed at identifying the highest-scoring translation, i.e.
• the mode.