@inproceedings{mannekote-etal-2025-making,
title = "Making Task-Oriented Dialogue Datasets More Natural by Synthetically Generating Indirect User Requests",
author = "Mannekote, Amogh and
Nam, Jinseok and
Li, Ziming and
Boyer, Kristy Elizabeth and
Dorr, Bonnie J.",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.696/",
pages = "10449--10459",
abstract = "Indirect User Requests (IURs), such as {\textquotedblleft}It`s cold in here{\textquotedblright} instead of {\textquotedblleft}Could you please increase the temperature?{\textquotedblright} are common in human-human task-oriented dialogue and require world knowledge and pragmatic reasoning from the listener. While large language models (LLMs) can handle these requests effectively, smaller models deployed on virtual assistants often struggle due to resource constraints. Moreover, existing task-oriented dialogue benchmarks lack sufficient examples of complex discourse phenomena such as indirectness. To address this, we propose a set of linguistic criteria along with an LLM-based pipeline for generating realistic IURs to test natural language understanding (NLU) and dialogue state tracking (DST) models before deployment in a new domain. We also release IndirectRequests, a dataset of IURs based on the Schema-Guided Dialogue (SGD) corpus, as a comparative testbed for evaluating the performance of smaller models in handling indirect requests."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mannekote-etal-2025-making">
<titleInfo>
<title>Making Task-Oriented Dialogue Datasets More Natural by Synthetically Generating Indirect User Requests</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amogh</namePart>
<namePart type="family">Mannekote</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinseok</namePart>
<namePart type="family">Nam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziming</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kristy</namePart>
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Boyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Dorr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Indirect User Requests (IURs), such as “It‘s cold in here” instead of “Could you please increase the temperature?” are common in human-human task-oriented dialogue and require world knowledge and pragmatic reasoning from the listener. While large language models (LLMs) can handle these requests effectively, smaller models deployed on virtual assistants often struggle due to resource constraints. Moreover, existing task-oriented dialogue benchmarks lack sufficient examples of complex discourse phenomena such as indirectness. To address this, we propose a set of linguistic criteria along with an LLM-based pipeline for generating realistic IURs to test natural language understanding (NLU) and dialogue state tracking (DST) models before deployment in a new domain. We also release IndirectRequests, a dataset of IURs based on the Schema-Guided Dialogue (SGD) corpus, as a comparative testbed for evaluating the performance of smaller models in handling indirect requests.</abstract>
<identifier type="citekey">mannekote-etal-2025-making</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.696/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>10449</start>
<end>10459</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Making Task-Oriented Dialogue Datasets More Natural by Synthetically Generating Indirect User Requests
%A Mannekote, Amogh
%A Nam, Jinseok
%A Li, Ziming
%A Boyer, Kristy Elizabeth
%A Dorr, Bonnie J.
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F mannekote-etal-2025-making
%X Indirect User Requests (IURs), such as “It‘s cold in here” instead of “Could you please increase the temperature?” are common in human-human task-oriented dialogue and require world knowledge and pragmatic reasoning from the listener. While large language models (LLMs) can handle these requests effectively, smaller models deployed on virtual assistants often struggle due to resource constraints. Moreover, existing task-oriented dialogue benchmarks lack sufficient examples of complex discourse phenomena such as indirectness. To address this, we propose a set of linguistic criteria along with an LLM-based pipeline for generating realistic IURs to test natural language understanding (NLU) and dialogue state tracking (DST) models before deployment in a new domain. We also release IndirectRequests, a dataset of IURs based on the Schema-Guided Dialogue (SGD) corpus, as a comparative testbed for evaluating the performance of smaller models in handling indirect requests.
%U https://aclanthology.org/2025.coling-main.696/
%P 10449-10459
Markdown (Informal)
[Making Task-Oriented Dialogue Datasets More Natural by Synthetically Generating Indirect User Requests](https://aclanthology.org/2025.coling-main.696/) (Mannekote et al., COLING 2025)
ACL