@inproceedings{jadhav-etal-2026-interpretable,
title = "Interpretable Text-Based Prosodic Boundary Prediction for {H}indi Children{'}s Stories",
author = "Jadhav, Sakshi and
Dhamne, Mansi and
Rao, Preeti",
editor = "Adelani, David Ifeoluwa and
Alabi, Jesujoba and
Arnett, Catherine and
Chang, Tyler and
Downey, C.M. and
Goldman, Omer and
Li, Senyu and
Miranda, Lester James Validad and
Qi, Jirui and
Stap, David and
Winata, Genta Indra and
Zhang, Xinyu Crystina",
booktitle = "Proceedings of the 6th Workshop on Multilingual Representation Learning ({MRL} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.mrl-1.36/",
pages = "455--466",
ISBN = "979-8-89176-469-9",
abstract = "Prosodic boundary prediction from text remains underexplored for morphologically rich languages such as Hindi. We present a comprehensive study of text-based prosodic boundary prediction for Hindi children{'}s texts using interpretable linguistic representations. We introduce a new corpus of 54 textbook passages annotated by six fluent Hindi speakers and formulate two complementary tasks: Prosodic Boundary Detection (PBD) and Forbidden Pause Detection (FPD). Analysis of the corpus shows that 42.6{\%} of majority-supported boundaries lack explicit punctuation, motivating the use of richer linguistic features beyond surface cues. Using a 28-feature linguistic representation, our models achieve F$_1$ scores of 0.89 (PBD) and 0.93 (FPD), while generalizing to an independently annotated Hindi corpus without retraining. We study the optimal feature set in terms of its differences from a previously published similar work in English, and also investigate the cross-lingual portability of the feature sets to draw insights that are supported by the structural differences between Hindi and English."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jadhav-etal-2026-interpretable">
<titleInfo>
<title>Interpretable Text-Based Prosodic Boundary Prediction for Hindi Children’s Stories</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sakshi</namePart>
<namePart type="family">Jadhav</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mansi</namePart>
<namePart type="family">Dhamne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preeti</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Workshop on Multilingual Representation Learning (MRL 2026)</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">Jesujoba</namePart>
<namePart type="family">Alabi</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">Tyler</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">C</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Downey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omer</namePart>
<namePart type="family">Goldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Senyu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lester</namePart>
<namePart type="given">James</namePart>
<namePart type="given">Validad</namePart>
<namePart type="family">Miranda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jirui</namePart>
<namePart type="family">Qi</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">Genta</namePart>
<namePart type="given">Indra</namePart>
<namePart type="family">Winata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyu</namePart>
<namePart type="given">Crystina</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-469-9</identifier>
</relatedItem>
<abstract>Prosodic boundary prediction from text remains underexplored for morphologically rich languages such as Hindi. We present a comprehensive study of text-based prosodic boundary prediction for Hindi children’s texts using interpretable linguistic representations. We introduce a new corpus of 54 textbook passages annotated by six fluent Hindi speakers and formulate two complementary tasks: Prosodic Boundary Detection (PBD) and Forbidden Pause Detection (FPD). Analysis of the corpus shows that 42.6% of majority-supported boundaries lack explicit punctuation, motivating the use of richer linguistic features beyond surface cues. Using a 28-feature linguistic representation, our models achieve F₁ scores of 0.89 (PBD) and 0.93 (FPD), while generalizing to an independently annotated Hindi corpus without retraining. We study the optimal feature set in terms of its differences from a previously published similar work in English, and also investigate the cross-lingual portability of the feature sets to draw insights that are supported by the structural differences between Hindi and English.</abstract>
<identifier type="citekey">jadhav-etal-2026-interpretable</identifier>
<location>
<url>https://aclanthology.org/2026.mrl-1.36/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>455</start>
<end>466</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Interpretable Text-Based Prosodic Boundary Prediction for Hindi Children’s Stories
%A Jadhav, Sakshi
%A Dhamne, Mansi
%A Rao, Preeti
%Y Adelani, David Ifeoluwa
%Y Alabi, Jesujoba
%Y Arnett, Catherine
%Y Chang, Tyler
%Y Downey, C. M.
%Y Goldman, Omer
%Y Li, Senyu
%Y Miranda, Lester James Validad
%Y Qi, Jirui
%Y Stap, David
%Y Winata, Genta Indra
%Y Zhang, Xinyu Crystina
%S Proceedings of the 6th Workshop on Multilingual Representation Learning (MRL 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-469-9
%F jadhav-etal-2026-interpretable
%X Prosodic boundary prediction from text remains underexplored for morphologically rich languages such as Hindi. We present a comprehensive study of text-based prosodic boundary prediction for Hindi children’s texts using interpretable linguistic representations. We introduce a new corpus of 54 textbook passages annotated by six fluent Hindi speakers and formulate two complementary tasks: Prosodic Boundary Detection (PBD) and Forbidden Pause Detection (FPD). Analysis of the corpus shows that 42.6% of majority-supported boundaries lack explicit punctuation, motivating the use of richer linguistic features beyond surface cues. Using a 28-feature linguistic representation, our models achieve F₁ scores of 0.89 (PBD) and 0.93 (FPD), while generalizing to an independently annotated Hindi corpus without retraining. We study the optimal feature set in terms of its differences from a previously published similar work in English, and also investigate the cross-lingual portability of the feature sets to draw insights that are supported by the structural differences between Hindi and English.
%U https://aclanthology.org/2026.mrl-1.36/
%P 455-466
Markdown (Informal)
[Interpretable Text-Based Prosodic Boundary Prediction for Hindi Children’s Stories](https://aclanthology.org/2026.mrl-1.36/) (Jadhav et al., MRL 2026)
ACL