Digging Errors in NMT: Evaluating and Understanding Model Errors from Partial Hypothesis Space
Digging Errors in NMT: Evaluating and Understanding Model Errors from Partial Hypothesis Space
Solid evaluation of neural machine translation (NMT) is key to its understanding and improvement. Current evaluation of an NMT system is usually built upon a heuristic decoding algorithm (e.g., beam search) and an evaluation metric assessing similarity between the translation and golden reference. However, this system-level evaluation framework is limited …