@inproceedings{casanueva-etal-2022-nlu,
title = "{NLU}++: A Multi-Label, Slot-Rich, Generalisable Dataset for Natural Language Understanding in Task-Oriented Dialogue",
author = "Casanueva, Inigo and
Vuli{\'c}, Ivan and
Spithourakis, Georgios and
Budzianowski, Pawe{\l}",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-naacl.154",
doi = "10.18653/v1/2022.findings-naacl.154",
pages = "1998--2013",
abstract = "We present NLU++, a novel dataset for natural language understanding (NLU) in task-oriented dialogue (ToD) systems, with the aim to provide a much more challenging evaluation environment for dialogue NLU models, up to date with the current application and industry requirements. NLU++ is divided into two domains (BANKING and HOTELS) and brings several crucial improvements over current commonly used NLU datasets. 1) NLU++ provides fine-grained domain ontologies with a large set of challenging multi-intent sentences combined with finer-grained and thus more challenging slot sets. 2) The ontology is divided into domain-specific and generic (i.e., domain-universal) intents that overlap across domains, promoting cross-domain reusability of annotated examples. 3) The dataset design has been inspired by the problems observed in industrial ToD systems, and 4) it has been collected, filtered and carefully annotated by dialogue NLU experts, yielding high-quality annotated data. Finally, we benchmark a series of current state-of-the-art NLU models on NLU++; the results demonstrate the challenging nature of the dataset, especially in low-data regimes, and call for further research on ToD NLU.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="casanueva-etal-2022-nlu">
<titleInfo>
<title>NLU++: A Multi-Label, Slot-Rich, Generalisable Dataset for Natural Language Understanding in Task-Oriented Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Inigo</namePart>
<namePart type="family">Casanueva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Vulić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georgios</namePart>
<namePart type="family">Spithourakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paweł</namePart>
<namePart type="family">Budzianowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present NLU++, a novel dataset for natural language understanding (NLU) in task-oriented dialogue (ToD) systems, with the aim to provide a much more challenging evaluation environment for dialogue NLU models, up to date with the current application and industry requirements. NLU++ is divided into two domains (BANKING and HOTELS) and brings several crucial improvements over current commonly used NLU datasets. 1) NLU++ provides fine-grained domain ontologies with a large set of challenging multi-intent sentences combined with finer-grained and thus more challenging slot sets. 2) The ontology is divided into domain-specific and generic (i.e., domain-universal) intents that overlap across domains, promoting cross-domain reusability of annotated examples. 3) The dataset design has been inspired by the problems observed in industrial ToD systems, and 4) it has been collected, filtered and carefully annotated by dialogue NLU experts, yielding high-quality annotated data. Finally, we benchmark a series of current state-of-the-art NLU models on NLU++; the results demonstrate the challenging nature of the dataset, especially in low-data regimes, and call for further research on ToD NLU.</abstract>
<identifier type="citekey">casanueva-etal-2022-nlu</identifier>
<identifier type="doi">10.18653/v1/2022.findings-naacl.154</identifier>
<location>
<url>https://aclanthology.org/2022.findings-naacl.154</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1998</start>
<end>2013</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NLU++: A Multi-Label, Slot-Rich, Generalisable Dataset for Natural Language Understanding in Task-Oriented Dialogue
%A Casanueva, Inigo
%A Vulić, Ivan
%A Spithourakis, Georgios
%A Budzianowski, Paweł
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Findings of the Association for Computational Linguistics: NAACL 2022
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F casanueva-etal-2022-nlu
%X We present NLU++, a novel dataset for natural language understanding (NLU) in task-oriented dialogue (ToD) systems, with the aim to provide a much more challenging evaluation environment for dialogue NLU models, up to date with the current application and industry requirements. NLU++ is divided into two domains (BANKING and HOTELS) and brings several crucial improvements over current commonly used NLU datasets. 1) NLU++ provides fine-grained domain ontologies with a large set of challenging multi-intent sentences combined with finer-grained and thus more challenging slot sets. 2) The ontology is divided into domain-specific and generic (i.e., domain-universal) intents that overlap across domains, promoting cross-domain reusability of annotated examples. 3) The dataset design has been inspired by the problems observed in industrial ToD systems, and 4) it has been collected, filtered and carefully annotated by dialogue NLU experts, yielding high-quality annotated data. Finally, we benchmark a series of current state-of-the-art NLU models on NLU++; the results demonstrate the challenging nature of the dataset, especially in low-data regimes, and call for further research on ToD NLU.
%R 10.18653/v1/2022.findings-naacl.154
%U https://aclanthology.org/2022.findings-naacl.154
%U https://doi.org/10.18653/v1/2022.findings-naacl.154
%P 1998-2013
Markdown (Informal)
[NLU++: A Multi-Label, Slot-Rich, Generalisable Dataset for Natural Language Understanding in Task-Oriented Dialogue](https://aclanthology.org/2022.findings-naacl.154) (Casanueva et al., Findings 2022)
ACL