Papers › Finding the Optimal Vocabulary Size for Neural Machine Translation

Finding the Optimal Vocabulary Size for Neural Machine Translation

5 Apr 2020Findings of the Association for Computational Linguistics 2020arXiv:2004.02334archive 2025-07-28

Thamme Gowda, Jonathan May

We cast neural machine translation (NMT) as a classification task in an autoregressive setting and analyze the limitations of both classification and autoregression components. Classifiers are known to perform better with balanced class distributions during training. Since the Zipfian nature of languages causes imbalanced classes, we explore its effect on NMT. We analyze the effect of various vocabulary sizes on NMT performance on multiple languages with many data sizes, and reveal an explanation for why certain vocabulary sizes are better than others.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

thammegowda/005-nmt-imbalance officialmentioned in paper report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ClassificationGeneral ClassificationMachine TranslationNMTTranslation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections