SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.08357 · ACL Findings · 2021

As Easy as 1, 2, 3: Behavioural Testing of NMT Systems for Numerical Translation

Jun Wang, Chang Xu, Benjamin Rubinstein, Francisco Guzmán, Trevor Cohn, Ahmed El-Kishky

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

Mistranslated numbers have the potential to cause serious effects, such as financial loss or medical misinformation. In this work we develop comprehensive assessments of the robustness of neural machine translation systems to numerical text via behavioural testing. We explore a variety of numerical translation capabilities a system is expected to exhibit and design effective test examples to expose system underperformance. We find that numerical mistranslation is a general issue: major commercial systems and state-of-the-art research models fail on many of our test examples, for high-and low-resource languages. Our tests reveal novel errors that have not previously been reported in NMT systems, to the best of our knowledge. Lastly, we discuss strategies to mitigate numerical mistranslation.

For agents

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

get_harvested_code_for_paper("2107.08357")
get_code_for_paper("2107.08357")
have("2107.08357")

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

curl https://syntology.ai/api/ran/2107.08357.json

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

[![Syntology run record](https://syntology.ai/api/ran/2107.08357.svg)](https://syntology.ai/paper/2107.08357)

Connect an agent — have() is free.