Breaking the Beam Search Curse: A Study of (Re-)Scoring Methods and Stopping Criteria for Neural Machine Translation
This solves a specific problem in neural machine translation for researchers and practitioners, offering incremental improvements over existing methods.
The paper tackles the problem where larger beam sizes in neural machine translation hurt translation quality, explaining why this happens and proposing methods with optimal stopping criteria to address it. Results show their hyperparameter-free methods outperform length normalization by +2.0 BLEU and achieve best results on Chinese-to-English translation.
Beam search is widely used in neural machine translation, and usually improves translation quality compared to greedy search. It has been widely observed that, however, beam sizes larger than 5 hurt translation quality. We explain why this happens, and propose several methods to address this problem. Furthermore, we discuss the optimal stopping criteria for these methods. Results show that our hyperparameter-free methods outperform the widely-used hyperparameter-free heuristic of length normalization by +2.0 BLEU, and achieve the best results among all methods on Chinese-to-English translation.