@inproceedings{irawan-etal-2025-entropy2vec,
title = "{E}ntropy2{V}ec: Crosslingual Language Modeling Entropy as End-to-End Learnable Language Representations",
author = "Irawan, Patrick Amadeus and
Diandaru, Ryandito and
Syuhada, Belati Jagad Bintang and
Suchrady, Randy Zakya and
Aji, Alham Fikri and
Winata, Genta Indra and
Koto, Fajri and
Cahyawijaya, Samuel",
editor = "Adelani, David Ifeoluwa and
Arnett, Catherine and
Ataman, Duygu and
Chang, Tyler A. and
Gonen, Hila and
Raja, Rahul and
Schmidt, Fabian and
Stap, David and
Wang, Jiayi",
booktitle = "Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025)",
month = nov,
year = "2025",
address = "Suzhuo, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.mrl-main.29/",
pages = "426--437",
ISBN = "979-8-89176-345-6",
abstract = "We introduce Entropy2Vec, a novel framework for deriving cross-lingual language representations by leveraging the entropy of monolingual language models. Unlike traditional typological inventories that suffer from feature sparsity and static snapshots, Entropy2Vec uses the inherent uncertainty in language models to capture typological relationships between languages. By training a language model on a single language, we hypothesize that the entropy of its predictions reflects its structural similarity to other languages: Low entropy indicates high similarity, while high entropy suggests greater divergence. This approach yields dense, non-sparse language embeddings that are adaptable to different timeframes and free from missing values. Empirical evaluations demonstrate that Entropy2Vec embeddings align with established typological categories and achieved competitive performance in downstream multilingual NLP tasks, such as those addressed by the LinguAlchemy framework."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="irawan-etal-2025-entropy2vec">
<titleInfo>
<title>Entropy2Vec: Crosslingual Language Modeling Entropy as End-to-End Learnable Language Representations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="given">Amadeus</namePart>
<namePart type="family">Irawan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryandito</namePart>
<namePart type="family">Diandaru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Belati</namePart>
<namePart type="given">Jagad</namePart>
<namePart type="given">Bintang</namePart>
<namePart type="family">Syuhada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Randy</namePart>
<namePart type="given">Zakya</namePart>
<namePart type="family">Suchrady</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alham</namePart>
<namePart type="given">Fikri</namePart>
<namePart type="family">Aji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Genta</namePart>
<namePart type="given">Indra</namePart>
<namePart type="family">Winata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fajri</namePart>
<namePart type="family">Koto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Cahyawijaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Ifeoluwa</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catherine</namePart>
<namePart type="family">Arnett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Duygu</namePart>
<namePart type="family">Ataman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tyler</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hila</namePart>
<namePart type="family">Gonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Raja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabian</namePart>
<namePart type="family">Schmidt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Stap</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiayi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhuo, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-345-6</identifier>
</relatedItem>
<abstract>We introduce Entropy2Vec, a novel framework for deriving cross-lingual language representations by leveraging the entropy of monolingual language models. Unlike traditional typological inventories that suffer from feature sparsity and static snapshots, Entropy2Vec uses the inherent uncertainty in language models to capture typological relationships between languages. By training a language model on a single language, we hypothesize that the entropy of its predictions reflects its structural similarity to other languages: Low entropy indicates high similarity, while high entropy suggests greater divergence. This approach yields dense, non-sparse language embeddings that are adaptable to different timeframes and free from missing values. Empirical evaluations demonstrate that Entropy2Vec embeddings align with established typological categories and achieved competitive performance in downstream multilingual NLP tasks, such as those addressed by the LinguAlchemy framework.</abstract>
<identifier type="citekey">irawan-etal-2025-entropy2vec</identifier>
<location>
<url>https://aclanthology.org/2025.mrl-main.29/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>426</start>
<end>437</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Entropy2Vec: Crosslingual Language Modeling Entropy as End-to-End Learnable Language Representations
%A Irawan, Patrick Amadeus
%A Diandaru, Ryandito
%A Syuhada, Belati Jagad Bintang
%A Suchrady, Randy Zakya
%A Aji, Alham Fikri
%A Winata, Genta Indra
%A Koto, Fajri
%A Cahyawijaya, Samuel
%Y Adelani, David Ifeoluwa
%Y Arnett, Catherine
%Y Ataman, Duygu
%Y Chang, Tyler A.
%Y Gonen, Hila
%Y Raja, Rahul
%Y Schmidt, Fabian
%Y Stap, David
%Y Wang, Jiayi
%S Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025)
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhuo, China
%@ 979-8-89176-345-6
%F irawan-etal-2025-entropy2vec
%X We introduce Entropy2Vec, a novel framework for deriving cross-lingual language representations by leveraging the entropy of monolingual language models. Unlike traditional typological inventories that suffer from feature sparsity and static snapshots, Entropy2Vec uses the inherent uncertainty in language models to capture typological relationships between languages. By training a language model on a single language, we hypothesize that the entropy of its predictions reflects its structural similarity to other languages: Low entropy indicates high similarity, while high entropy suggests greater divergence. This approach yields dense, non-sparse language embeddings that are adaptable to different timeframes and free from missing values. Empirical evaluations demonstrate that Entropy2Vec embeddings align with established typological categories and achieved competitive performance in downstream multilingual NLP tasks, such as those addressed by the LinguAlchemy framework.
%U https://aclanthology.org/2025.mrl-main.29/
%P 426-437
Markdown (Informal)
[Entropy2Vec: Crosslingual Language Modeling Entropy as End-to-End Learnable Language Representations](https://aclanthology.org/2025.mrl-main.29/) (Irawan et al., MRL 2025)
ACL
- Patrick Amadeus Irawan, Ryandito Diandaru, Belati Jagad Bintang Syuhada, Randy Zakya Suchrady, Alham Fikri Aji, Genta Indra Winata, Fajri Koto, and Samuel Cahyawijaya. 2025. Entropy2Vec: Crosslingual Language Modeling Entropy as End-to-End Learnable Language Representations. In Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025), pages 426–437, Suzhuo, China. Association for Computational Linguistics.