@inproceedings{boldt-mortensen-2024-xferbench,
title = "{X}fer{B}ench: a Data-Driven Benchmark for Emergent Language",
author = "Boldt, Brendon and
Mortensen, David",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.82",
doi = "10.18653/v1/2024.naacl-long.82",
pages = "1475--1489",
abstract = "In this paper, we introduce a benchmark for evaluating the overall quality of emergent languages using data-driven methods. Specifically, we interpret the notion of the {``}quality{''} of an emergent language as its similarity to human language within a deep learning framework. We measure this by using the emergent language as pretraining data for a downstream NLP tasks in human language{---}the better the downstream performance, the better the emergent language. We implement this benchmark as an easy-to-use Python package that only requires a text file of utterances from the emergent language to be evaluated. Finally, we empirically test the benchmark{'}s validity using human, synthetic, and emergent language baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="boldt-mortensen-2024-xferbench">
<titleInfo>
<title>XferBench: a Data-Driven Benchmark for Emergent Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Brendon</namePart>
<namePart type="family">Boldt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Mortensen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we introduce a benchmark for evaluating the overall quality of emergent languages using data-driven methods. Specifically, we interpret the notion of the “quality” of an emergent language as its similarity to human language within a deep learning framework. We measure this by using the emergent language as pretraining data for a downstream NLP tasks in human language—the better the downstream performance, the better the emergent language. We implement this benchmark as an easy-to-use Python package that only requires a text file of utterances from the emergent language to be evaluated. Finally, we empirically test the benchmark’s validity using human, synthetic, and emergent language baselines.</abstract>
<identifier type="citekey">boldt-mortensen-2024-xferbench</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-long.82</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.82</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>1475</start>
<end>1489</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T XferBench: a Data-Driven Benchmark for Emergent Language
%A Boldt, Brendon
%A Mortensen, David
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F boldt-mortensen-2024-xferbench
%X In this paper, we introduce a benchmark for evaluating the overall quality of emergent languages using data-driven methods. Specifically, we interpret the notion of the “quality” of an emergent language as its similarity to human language within a deep learning framework. We measure this by using the emergent language as pretraining data for a downstream NLP tasks in human language—the better the downstream performance, the better the emergent language. We implement this benchmark as an easy-to-use Python package that only requires a text file of utterances from the emergent language to be evaluated. Finally, we empirically test the benchmark’s validity using human, synthetic, and emergent language baselines.
%R 10.18653/v1/2024.naacl-long.82
%U https://aclanthology.org/2024.naacl-long.82
%U https://doi.org/10.18653/v1/2024.naacl-long.82
%P 1475-1489
Markdown (Informal)
[XferBench: a Data-Driven Benchmark for Emergent Language](https://aclanthology.org/2024.naacl-long.82) (Boldt & Mortensen, NAACL 2024)
ACL
- Brendon Boldt and David Mortensen. 2024. XferBench: a Data-Driven Benchmark for Emergent Language. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 1475–1489, Mexico City, Mexico. Association for Computational Linguistics.