@inproceedings{qharabagh-etal-2025-fast,
title = "Fast, Not Fancy: Rethinking {G}2{P} with Rich Data and Statistical Models",
author = "Qharabagh, Mahta Fetrat and
Dehghanian, Zahra and
Rabiee, Hamid R.",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.1218/",
doi = "10.18653/v1/2025.findings-emnlp.1218",
pages = "22382--22408",
ISBN = "979-8-89176-335-7",
abstract = "Homograph disambiguation remains a significant challenge in grapheme-to-phoneme (G2P) conversion, especially for low-resource languages. This challenge is twofold: (1) creating balanced and comprehensive homograph datasets is labor-intensive and costly, and (2) specific disambiguation strategies introduce additional latency, making them unsuitable for real-time applications such as screen readers and other accessibility tools. In this paper, we address both issues. First, we propose a semi-automated pipeline for constructing homograph-focused datasets, introduce the HomoRich dataset generated through this pipeline, and demonstrate its effectiveness by applying it to enhance a state-of-the-art deep learning-based G2P system for Persian. Second, we advocate for a paradigm shift{---}utilizing rich offline datasets to inform the development of fast, statistical methods suitable for latency-sensitive accessibility applications like screen readers. To this end, we improve one of the most well-known rule-based G2P systems, eSpeak, into a fast homograph-aware version, HomoFast eSpeak. Our results show an approximate 30 percentage-point improvement in homograph disambiguation accuracy for the deep learning-based and eSpeak systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qharabagh-etal-2025-fast">
<titleInfo>
<title>Fast, Not Fancy: Rethinking G2P with Rich Data and Statistical Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mahta</namePart>
<namePart type="given">Fetrat</namePart>
<namePart type="family">Qharabagh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zahra</namePart>
<namePart type="family">Dehghanian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamid</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Rabiee</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>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Homograph disambiguation remains a significant challenge in grapheme-to-phoneme (G2P) conversion, especially for low-resource languages. This challenge is twofold: (1) creating balanced and comprehensive homograph datasets is labor-intensive and costly, and (2) specific disambiguation strategies introduce additional latency, making them unsuitable for real-time applications such as screen readers and other accessibility tools. In this paper, we address both issues. First, we propose a semi-automated pipeline for constructing homograph-focused datasets, introduce the HomoRich dataset generated through this pipeline, and demonstrate its effectiveness by applying it to enhance a state-of-the-art deep learning-based G2P system for Persian. Second, we advocate for a paradigm shift—utilizing rich offline datasets to inform the development of fast, statistical methods suitable for latency-sensitive accessibility applications like screen readers. To this end, we improve one of the most well-known rule-based G2P systems, eSpeak, into a fast homograph-aware version, HomoFast eSpeak. Our results show an approximate 30 percentage-point improvement in homograph disambiguation accuracy for the deep learning-based and eSpeak systems.</abstract>
<identifier type="citekey">qharabagh-etal-2025-fast</identifier>
<identifier type="doi">10.18653/v1/2025.findings-emnlp.1218</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.1218/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>22382</start>
<end>22408</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fast, Not Fancy: Rethinking G2P with Rich Data and Statistical Models
%A Qharabagh, Mahta Fetrat
%A Dehghanian, Zahra
%A Rabiee, Hamid R.
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F qharabagh-etal-2025-fast
%X Homograph disambiguation remains a significant challenge in grapheme-to-phoneme (G2P) conversion, especially for low-resource languages. This challenge is twofold: (1) creating balanced and comprehensive homograph datasets is labor-intensive and costly, and (2) specific disambiguation strategies introduce additional latency, making them unsuitable for real-time applications such as screen readers and other accessibility tools. In this paper, we address both issues. First, we propose a semi-automated pipeline for constructing homograph-focused datasets, introduce the HomoRich dataset generated through this pipeline, and demonstrate its effectiveness by applying it to enhance a state-of-the-art deep learning-based G2P system for Persian. Second, we advocate for a paradigm shift—utilizing rich offline datasets to inform the development of fast, statistical methods suitable for latency-sensitive accessibility applications like screen readers. To this end, we improve one of the most well-known rule-based G2P systems, eSpeak, into a fast homograph-aware version, HomoFast eSpeak. Our results show an approximate 30 percentage-point improvement in homograph disambiguation accuracy for the deep learning-based and eSpeak systems.
%R 10.18653/v1/2025.findings-emnlp.1218
%U https://aclanthology.org/2025.findings-emnlp.1218/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.1218
%P 22382-22408
Markdown (Informal)
[Fast, Not Fancy: Rethinking G2P with Rich Data and Statistical Models](https://aclanthology.org/2025.findings-emnlp.1218/) (Qharabagh et al., Findings 2025)
ACL