SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.05294 · EMNLP · 2023

Hi Guys or Hi Folks? Benchmarking Gender-Neutral Machine Translation with the GeNTE Corpus

Matteo Negri, Beatrice Savoldi, Luisa Bentivogli, Dennis Fucci, Andrea Piergentili

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 9 functions out of this paper's own repositories and ran 9 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
hlt-mt/fbk-NEUTR-evAL canonical 9 of 9
FunctionStatusWhere it lives
add_args Ran hlt-mt/fbk-NEUTR-evAL/src/fbk_neutreval/cli/llm_as_a_judge/generic.py
code served (permissive licence) · get_code("80132b7e673543b4")
evaluate_word Ran hlt-mt/fbk-NEUTR-evAL/src/fbk_neutreval/cli/neogate_evaluation.py
code served (permissive licence) · get_code("e345cd5a78d9e4d7")
get_annotations Ran hlt-mt/fbk-NEUTR-evAL/src/fbk_neutreval/cli/neogate_evaluation.py
code served (permissive licence) · get_code("0a86d4b3dbe47b96")
load_data Ran hlt-mt/fbk-NEUTR-evAL/src/fbk_neutreval/data_preprocessing.py
code served (permissive licence) · get_code("190813b8b0b50ec4")
load_input Ran hlt-mt/fbk-NEUTR-evAL/src/fbk_neutreval/cli/llm_as_a_judge/generic.py
code served (permissive licence) · get_code("892866bfc3e91243")
load_prompt_message Ran hlt-mt/fbk-NEUTR-evAL/src/fbk_neutreval/cli/llm_as_a_judge/generic.py
code served (permissive licence) · get_code("f6cd896bf69d3250")
register_metric Ran hlt-mt/fbk-NEUTR-evAL/src/fbk_neutreval/metrics.py
code served (permissive licence) · get_code("133929a3d25c4e6b")
register_writer Ran hlt-mt/fbk-NEUTR-evAL/src/fbk_neutreval/writers.py
code served (permissive licence) · get_code("3859afc337659810")
to_words Ran hlt-mt/fbk-NEUTR-evAL/src/fbk_neutreval/cli/neogate_evaluation.py
code served (permissive licence) · get_code("ab107c6f8d1818aa")

Repositories linked to this paper

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

Abstract

Gender inequality is embedded in our communication practices and perpetuated in translation technologies. This becomes particularly apparent when translating into grammatical gender languages, where machine translation (MT) often defaults to masculine and stereotypical representations by making undue binary gender assumptions. Our work addresses the rising demand for inclusive language by focusing head-on on gender-neutral translation from English to Italian. We start from the essentials: proposing a dedicated benchmark and exploring automated evaluation methods. First, we introduce GeNTE, a natural, bilingual test set for gender-neutral translation, whose creation was informed by a survey on the perception and use of neutral language. Based on GeNTE, we then overview existing reference-based evaluation approaches, highlight their limits, and propose a reference-free method more suitable to assess gender-neutral translation.

For agents

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

get_harvested_code_for_paper("2310.05294")
get_code_for_paper("2310.05294")
have("2310.05294")

Connect an agent — have() is free.