SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1907.01968 · 2019

Depth Growing for Neural Machine Translation

arXiv · PDF · Open in the Atlas

Code that ran

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.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

While very deep neural networks have shown effectiveness for computer vision and text classification applications, how to increase the network depth of neural machine translation (NMT) models for better translation quality remains a challenging problem. Directly stacking more blocks to the NMT model results in no improvement and even reduces performance. In this work, we propose an effective two-stage approach with three specially designed components to construct deeper NMT models, which result in significant improvements over the strong Transformer baselines on WMT$14$ English$\to$German and English$\to$French translation tasks\footnote{Our code is available at \url{https://github.com/apeterswu/Depth_Growing_NMT}}.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1907.01968")
get_code_for_paper("1907.01968")
have("1907.01968")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1907.01968.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1907.01968.svg)](https://syntology.ai/paper/1907.01968)

Connect an agent — have() is free.