We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2004.02334")
get_code_for_paper("2004.02334")
have("2004.02334")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2004.02334.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2004.02334)
Connect an agent — have() is free.