SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2205.04067 · ACL · 2022

Sub-Word Alignment is Still Useful: A Vest-Pocket Method for Enhancing Low-Resource Machine Translation

Yu Hong, Minhan Xu

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

We leverage embedding duplication between aligned sub-words to extend the Parent-Child transfer learning method, so as to improve lowresource machine translation. We conduct experiments on benchmark datasets of My→En, Id→En and Tr→En translation scenarios. The test results show that our method produces substantial improvements, achieving the BLEU scores of 22.5, 28.0 and 18.1 respectively. In addition, the method is computationally efficient which reduces the consumption of training time by 63.8%, reaching the duration of 1.6 hours when training on a Tesla 16GB P100 GPU. All the models and source codes in the experiments will be made publicly available to support reproducible research.

For agents

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

get_harvested_code_for_paper("2205.04067")
get_code_for_paper("2205.04067")
have("2205.04067")

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

curl https://syntology.ai/api/ran/2205.04067.json

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

[![Syntology run record](https://syntology.ai/api/ran/2205.04067.svg)](https://syntology.ai/paper/2205.04067)

Connect an agent — have() is free.