SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.07429 · 2021

First the worst: Finding better gender translations during beam search

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

Neural machine translation inference procedures like beam search generate the most likely output under the model. This can exacerbate any demographic biases exhibited by the model. We focus on gender bias resulting from systematic errors in grammatical gender translation, which can lead to human referents being misrepresented or misgendered. Most approaches to this problem adjust the training data or the model. By contrast, we experiment with simply adjusting the inference procedure. We experiment with reranking nbest lists using gender features obtained automatically from the source sentence, and applying gender constraints while decoding to improve nbest list gender diversity. We find that a combination of these techniques allows large gains in WinoMT accuracy without requiring additional bilingual data or an additional NMT model.

For agents

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

get_harvested_code_for_paper("2104.07429")
get_code_for_paper("2104.07429")
have("2104.07429")

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

curl https://syntology.ai/api/ran/2104.07429.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.07429.svg)](https://syntology.ai/paper/2104.07429)

Connect an agent — have() is free.