@inproceedings{gaspers-etal-2022-temporal,
title = "Temporal Generalization for Spoken Language Understanding",
author = "Gaspers, Judith and
Kumar, Anoop and
Ver Steeg, Greg and
Galstyan, Aram",
editor = "Loukina, Anastassia and
Gangadharaiah, Rashmi and
Min, Bonan",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track",
month = jul,
year = "2022",
address = "Hybrid: Seattle, Washington + Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-industry.5",
doi = "10.18653/v1/2022.naacl-industry.5",
pages = "37--44",
abstract = "Spoken Language Understanding (SLU) models in industry applications are usually trained offline on historic data, but have to perform well on incoming user requests after deployment. Since the application data is not available at training time, this is formally similar to the domain generalization problem, where domains correspond to different temporal segments of the data, and the goal is to build a model that performs well on unseen domains, e.g., upcoming data. In this paper, we explore different strategies for achieving good temporal generalization, including instance weighting, temporal fine-tuning, learning temporal features and building a temporally-invariant model. Our results on data of large-scale SLU systems show that temporal information can be leveraged to improve temporal generalization for SLU models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gaspers-etal-2022-temporal">
<titleInfo>
<title>Temporal Generalization for Spoken Language Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Judith</namePart>
<namePart type="family">Gaspers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Ver Steeg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aram</namePart>
<namePart type="family">Galstyan</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>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anastassia</namePart>
<namePart type="family">Loukina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rashmi</namePart>
<namePart type="family">Gangadharaiah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bonan</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hybrid: Seattle, Washington + Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Spoken Language Understanding (SLU) models in industry applications are usually trained offline on historic data, but have to perform well on incoming user requests after deployment. Since the application data is not available at training time, this is formally similar to the domain generalization problem, where domains correspond to different temporal segments of the data, and the goal is to build a model that performs well on unseen domains, e.g., upcoming data. In this paper, we explore different strategies for achieving good temporal generalization, including instance weighting, temporal fine-tuning, learning temporal features and building a temporally-invariant model. Our results on data of large-scale SLU systems show that temporal information can be leveraged to improve temporal generalization for SLU models.</abstract>
<identifier type="citekey">gaspers-etal-2022-temporal</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-industry.5</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-industry.5</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>37</start>
<end>44</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Temporal Generalization for Spoken Language Understanding
%A Gaspers, Judith
%A Kumar, Anoop
%A Ver Steeg, Greg
%A Galstyan, Aram
%Y Loukina, Anastassia
%Y Gangadharaiah, Rashmi
%Y Min, Bonan
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track
%D 2022
%8 July
%I Association for Computational Linguistics
%C Hybrid: Seattle, Washington + Online
%F gaspers-etal-2022-temporal
%X Spoken Language Understanding (SLU) models in industry applications are usually trained offline on historic data, but have to perform well on incoming user requests after deployment. Since the application data is not available at training time, this is formally similar to the domain generalization problem, where domains correspond to different temporal segments of the data, and the goal is to build a model that performs well on unseen domains, e.g., upcoming data. In this paper, we explore different strategies for achieving good temporal generalization, including instance weighting, temporal fine-tuning, learning temporal features and building a temporally-invariant model. Our results on data of large-scale SLU systems show that temporal information can be leveraged to improve temporal generalization for SLU models.
%R 10.18653/v1/2022.naacl-industry.5
%U https://aclanthology.org/2022.naacl-industry.5
%U https://doi.org/10.18653/v1/2022.naacl-industry.5
%P 37-44
Markdown (Informal)
[Temporal Generalization for Spoken Language Understanding](https://aclanthology.org/2022.naacl-industry.5) (Gaspers et al., NAACL 2022)
ACL
- Judith Gaspers, Anoop Kumar, Greg Ver Steeg, and Aram Galstyan. 2022. Temporal Generalization for Spoken Language Understanding. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track, pages 37–44, Hybrid: Seattle, Washington + Online. Association for Computational Linguistics.