@inproceedings{malhotra-etal-2025-smart,
title = "{SMART}: Scalable Multilingual Approach for a Robust {TOD} System",
author = "Malhotra, Karan and
Jain, Arihant and
Aggarwal, Purav and
Saladi, Anoop",
editor = "Potdar, Saloni and
Rojas-Barahona, Lina and
Montella, Sebastien",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = nov,
year = "2025",
address = "Suzhou (China)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-industry.108/",
doi = "10.18653/v1/2025.emnlp-industry.108",
pages = "1543--1554",
ISBN = "979-8-89176-333-3",
abstract = "Task-Oriented Dialogue (TOD) systems have become increasingly important for real-world applications, yet existing frameworks face significant challenges in handling unstructured information, providing multilingual support, and engaging proactively. We propose SMART (Scalable Multilingual Approach for a Robust TOD System), a novel TOD framework that effectively addresses these limitations. SMART combines traditional pipeline elements with modern agent-based approaches, featuring a simplified dialogue state, intelligent clarification mechanisms, and a unified natural language generation component that eliminates response redundancy. Through comprehensive evaluation on troubleshooting and medical domains, we demonstrate that SMART outperforms baseline systems across key metrics. The system{'}s modular approach enables efficient scaling to new languages, as demonstrated through Spanish and Arabic languages. Integration of SMART in an e-commerce store resulted in reduction in product return rates, highlighting its industry impact. Our results establish SMART as an effective approach for building robust, scalable TOD systems that meet real-world requirements."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="malhotra-etal-2025-smart">
<titleInfo>
<title>SMART: Scalable Multilingual Approach for a Robust TOD System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Karan</namePart>
<namePart type="family">Malhotra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arihant</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Purav</namePart>
<namePart type="family">Aggarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Saladi</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 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saloni</namePart>
<namePart type="family">Potdar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lina</namePart>
<namePart type="family">Rojas-Barahona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastien</namePart>
<namePart type="family">Montella</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">979-8-89176-333-3</identifier>
</relatedItem>
<abstract>Task-Oriented Dialogue (TOD) systems have become increasingly important for real-world applications, yet existing frameworks face significant challenges in handling unstructured information, providing multilingual support, and engaging proactively. We propose SMART (Scalable Multilingual Approach for a Robust TOD System), a novel TOD framework that effectively addresses these limitations. SMART combines traditional pipeline elements with modern agent-based approaches, featuring a simplified dialogue state, intelligent clarification mechanisms, and a unified natural language generation component that eliminates response redundancy. Through comprehensive evaluation on troubleshooting and medical domains, we demonstrate that SMART outperforms baseline systems across key metrics. The system’s modular approach enables efficient scaling to new languages, as demonstrated through Spanish and Arabic languages. Integration of SMART in an e-commerce store resulted in reduction in product return rates, highlighting its industry impact. Our results establish SMART as an effective approach for building robust, scalable TOD systems that meet real-world requirements.</abstract>
<identifier type="citekey">malhotra-etal-2025-smart</identifier>
<identifier type="doi">10.18653/v1/2025.emnlp-industry.108</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-industry.108/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>1543</start>
<end>1554</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SMART: Scalable Multilingual Approach for a Robust TOD System
%A Malhotra, Karan
%A Jain, Arihant
%A Aggarwal, Purav
%A Saladi, Anoop
%Y Potdar, Saloni
%Y Rojas-Barahona, Lina
%Y Montella, Sebastien
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou (China)
%@ 979-8-89176-333-3
%F malhotra-etal-2025-smart
%X Task-Oriented Dialogue (TOD) systems have become increasingly important for real-world applications, yet existing frameworks face significant challenges in handling unstructured information, providing multilingual support, and engaging proactively. We propose SMART (Scalable Multilingual Approach for a Robust TOD System), a novel TOD framework that effectively addresses these limitations. SMART combines traditional pipeline elements with modern agent-based approaches, featuring a simplified dialogue state, intelligent clarification mechanisms, and a unified natural language generation component that eliminates response redundancy. Through comprehensive evaluation on troubleshooting and medical domains, we demonstrate that SMART outperforms baseline systems across key metrics. The system’s modular approach enables efficient scaling to new languages, as demonstrated through Spanish and Arabic languages. Integration of SMART in an e-commerce store resulted in reduction in product return rates, highlighting its industry impact. Our results establish SMART as an effective approach for building robust, scalable TOD systems that meet real-world requirements.
%R 10.18653/v1/2025.emnlp-industry.108
%U https://aclanthology.org/2025.emnlp-industry.108/
%U https://doi.org/10.18653/v1/2025.emnlp-industry.108
%P 1543-1554
Markdown (Informal)
[SMART: Scalable Multilingual Approach for a Robust TOD System](https://aclanthology.org/2025.emnlp-industry.108/) (Malhotra et al., EMNLP 2025)
ACL
- Karan Malhotra, Arihant Jain, Purav Aggarwal, and Anoop Saladi. 2025. SMART: Scalable Multilingual Approach for a Robust TOD System. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 1543–1554, Suzhou (China). Association for Computational Linguistics.