@inproceedings{padhye-vaidya-2026-lock,
title = "The Lock, Stock, and Barrel of {M}arathi Multiwords",
author = "Padhye, Aakanksha and
Vaidya, Ashwini",
editor = {Ojha, Atul Kr. and
Mititelu, Verginica Barbu and
Constant, Mathieu and
Stoyanova, Ivelina and
Do{\u{g}}ru{\"o}z, A. Seza and
Rademaker, Alexandre},
booktitle = "Proceedings of the 22nd Workshop on Multiword Expressions ({MWE} 2026)",
month = mar,
year = "2026",
address = "Rabat, Marocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.mwe-1.11/",
pages = "96--102",
ISBN = "979-8-89176-363-0",
abstract = "Multiword expressions are an important area of study in linguistics and natural language processing as they represent combination of words that function as a single unit, and display properties that cannot be predicated fully from their individual components. This paper describes annotated corpora of about 3000 multiword expressions across syntactic categories in Marathi. This is the first exhaustive resource for Marathi which includes both verbal and non-verbal multiwords. In order to develop the guidelines for annotation, we have used the existing literature on the identification and classification of these expressions. Following the PARSEME 2.0 guidelines, we discuss the categories of multiwords and their behaviour in the corpus. Throughout the annotation process, we encounter variability in compositionality and syntactic realization and discuss our design decisions during annotation. Such a dataset will further our understanding of how grammatical structure can be integrated with lexically stored multiword units in Marathi."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="padhye-vaidya-2026-lock">
<titleInfo>
<title>The Lock, Stock, and Barrel of Marathi Multiwords</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aakanksha</namePart>
<namePart type="family">Padhye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashwini</namePart>
<namePart type="family">Vaidya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Workshop on Multiword Expressions (MWE 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Verginica</namePart>
<namePart type="given">Barbu</namePart>
<namePart type="family">Mititelu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mathieu</namePart>
<namePart type="family">Constant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivelina</namePart>
<namePart type="family">Stoyanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandre</namePart>
<namePart type="family">Rademaker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Marocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-363-0</identifier>
</relatedItem>
<abstract>Multiword expressions are an important area of study in linguistics and natural language processing as they represent combination of words that function as a single unit, and display properties that cannot be predicated fully from their individual components. This paper describes annotated corpora of about 3000 multiword expressions across syntactic categories in Marathi. This is the first exhaustive resource for Marathi which includes both verbal and non-verbal multiwords. In order to develop the guidelines for annotation, we have used the existing literature on the identification and classification of these expressions. Following the PARSEME 2.0 guidelines, we discuss the categories of multiwords and their behaviour in the corpus. Throughout the annotation process, we encounter variability in compositionality and syntactic realization and discuss our design decisions during annotation. Such a dataset will further our understanding of how grammatical structure can be integrated with lexically stored multiword units in Marathi.</abstract>
<identifier type="citekey">padhye-vaidya-2026-lock</identifier>
<location>
<url>https://aclanthology.org/2026.mwe-1.11/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>96</start>
<end>102</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Lock, Stock, and Barrel of Marathi Multiwords
%A Padhye, Aakanksha
%A Vaidya, Ashwini
%Y Ojha, Atul Kr.
%Y Mititelu, Verginica Barbu
%Y Constant, Mathieu
%Y Stoyanova, Ivelina
%Y Doğruöz, A. Seza
%Y Rademaker, Alexandre
%S Proceedings of the 22nd Workshop on Multiword Expressions (MWE 2026)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Marocco
%@ 979-8-89176-363-0
%F padhye-vaidya-2026-lock
%X Multiword expressions are an important area of study in linguistics and natural language processing as they represent combination of words that function as a single unit, and display properties that cannot be predicated fully from their individual components. This paper describes annotated corpora of about 3000 multiword expressions across syntactic categories in Marathi. This is the first exhaustive resource for Marathi which includes both verbal and non-verbal multiwords. In order to develop the guidelines for annotation, we have used the existing literature on the identification and classification of these expressions. Following the PARSEME 2.0 guidelines, we discuss the categories of multiwords and their behaviour in the corpus. Throughout the annotation process, we encounter variability in compositionality and syntactic realization and discuss our design decisions during annotation. Such a dataset will further our understanding of how grammatical structure can be integrated with lexically stored multiword units in Marathi.
%U https://aclanthology.org/2026.mwe-1.11/
%P 96-102
Markdown (Informal)
[The Lock, Stock, and Barrel of Marathi Multiwords](https://aclanthology.org/2026.mwe-1.11/) (Padhye & Vaidya, MWE 2026)
ACL