SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.04020 · EMNLP · 2021

Distributionally Robust Multilingual Machine Translation

Marjan Ghazvininejad, Graham Neubig, Daniel Levy, Chunting Zhou, Xian Li

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

Multilingual neural machine translation (MNMT) learns to translate multiple language pairs with a single model, potentially improving both the accuracy and the memoryefficiency of deployed models. However, the heavy data imbalance between languages hinders the model from performing uniformly across language pairs. In this paper, we propose a new learning objective for MNMT based on distributionally robust optimization, which minimizes the worst-case expected loss over the set of language pairs. We further show how to practically optimize this objective for large translation corpora using an iterated best response scheme, which is both effective and incurs negligible additional computational cost compared to standard empirical risk minimization. We perform extensive experiments on three sets of languages from two datasets and show that our method consistently outperforms strong baseline methods in terms of average and per-language performance under both many-to-one and one-to-many translation settings. 1

For agents

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

get_harvested_code_for_paper("2109.04020")
get_code_for_paper("2109.04020")
have("2109.04020")

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

curl https://syntology.ai/api/ran/2109.04020.json

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

[![Syntology run record](https://syntology.ai/api/ran/2109.04020.svg)](https://syntology.ai/paper/2109.04020)

Connect an agent — have() is free.