@inproceedings{brutans-bloem-2025-automatic,
title = "Automatic {A}nimacy Classification for {L}atvian Nouns",
author = "Brut{\={a}}ns, Ralfs and
Bloem, Jelke",
editor = "Das, Sudhansu Bala and
Mishra, Pruthwik and
Singh, Alok and
Muhammad, Shamsuddeen Hassan and
Ekbal, Asif and
Das, Uday Kumar",
booktitle = "Proceedings of the Workshop on Beyond English: Natural Language Processing for all Languages in an Era of Large Language Models",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, BULGARIA",
url = "https://aclanthology.org/2025.globalnlp-1.11/",
pages = "90--97",
abstract = "We introduce the first automatic animacy classifier for the Latvian language. Animacy, a linguistic feature indicating whether a noun refers to a living entity, plays an important role in Latvian grammatical structures and syntactic agreement, but remains unexplored in Latvian NLP. We adapt and extend existing methods to develop type-based animacy classifiers that distinguish between human and non-human nouns. Due to the limited utility of Latvian WordNet, the classifier{'}s training data was derived from the WordNets of Lithuanian, English, and Japanese. These lists were intersected and mapped to Latvian nouns from the T{\={e}}zaurs dictionary through automatic translation. The resulting dataset was used to train classifiers with fastText and LVBERT embeddings. Results show good performance from a MLP classifier using the last four layers of LVBERT, with Lithuanian data contributing more than English. This demonstrates a viable method for animacy classification in languages lacking robust lexical resources and shows potential for broader application in morphologically rich, under-resourced languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="brutans-bloem-2025-automatic">
<titleInfo>
<title>Automatic Animacy Classification for Latvian Nouns</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ralfs</namePart>
<namePart type="family">Brutāns</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jelke</namePart>
<namePart type="family">Bloem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Beyond English: Natural Language Processing for all Languages in an Era of Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sudhansu</namePart>
<namePart type="given">Bala</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pruthwik</namePart>
<namePart type="family">Mishra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alok</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shamsuddeen</namePart>
<namePart type="given">Hassan</namePart>
<namePart type="family">Muhammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Uday</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, BULGARIA</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce the first automatic animacy classifier for the Latvian language. Animacy, a linguistic feature indicating whether a noun refers to a living entity, plays an important role in Latvian grammatical structures and syntactic agreement, but remains unexplored in Latvian NLP. We adapt and extend existing methods to develop type-based animacy classifiers that distinguish between human and non-human nouns. Due to the limited utility of Latvian WordNet, the classifier’s training data was derived from the WordNets of Lithuanian, English, and Japanese. These lists were intersected and mapped to Latvian nouns from the Tēzaurs dictionary through automatic translation. The resulting dataset was used to train classifiers with fastText and LVBERT embeddings. Results show good performance from a MLP classifier using the last four layers of LVBERT, with Lithuanian data contributing more than English. This demonstrates a viable method for animacy classification in languages lacking robust lexical resources and shows potential for broader application in morphologically rich, under-resourced languages.</abstract>
<identifier type="citekey">brutans-bloem-2025-automatic</identifier>
<location>
<url>https://aclanthology.org/2025.globalnlp-1.11/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>90</start>
<end>97</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Animacy Classification for Latvian Nouns
%A Brutāns, Ralfs
%A Bloem, Jelke
%Y Das, Sudhansu Bala
%Y Mishra, Pruthwik
%Y Singh, Alok
%Y Muhammad, Shamsuddeen Hassan
%Y Ekbal, Asif
%Y Das, Uday Kumar
%S Proceedings of the Workshop on Beyond English: Natural Language Processing for all Languages in an Era of Large Language Models
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, BULGARIA
%C Varna, Bulgaria
%F brutans-bloem-2025-automatic
%X We introduce the first automatic animacy classifier for the Latvian language. Animacy, a linguistic feature indicating whether a noun refers to a living entity, plays an important role in Latvian grammatical structures and syntactic agreement, but remains unexplored in Latvian NLP. We adapt and extend existing methods to develop type-based animacy classifiers that distinguish between human and non-human nouns. Due to the limited utility of Latvian WordNet, the classifier’s training data was derived from the WordNets of Lithuanian, English, and Japanese. These lists were intersected and mapped to Latvian nouns from the Tēzaurs dictionary through automatic translation. The resulting dataset was used to train classifiers with fastText and LVBERT embeddings. Results show good performance from a MLP classifier using the last four layers of LVBERT, with Lithuanian data contributing more than English. This demonstrates a viable method for animacy classification in languages lacking robust lexical resources and shows potential for broader application in morphologically rich, under-resourced languages.
%U https://aclanthology.org/2025.globalnlp-1.11/
%P 90-97
Markdown (Informal)
[Automatic Animacy Classification for Latvian Nouns](https://aclanthology.org/2025.globalnlp-1.11/) (Brutāns & Bloem, GlobalNLP 2025)
ACL
- Ralfs Brutāns and Jelke Bloem. 2025. Automatic Animacy Classification for Latvian Nouns. In Proceedings of the Workshop on Beyond English: Natural Language Processing for all Languages in an Era of Large Language Models, pages 90–97, Varna, Bulgaria. INCOMA Ltd., Shoumen, BULGARIA.