@inproceedings{do-etal-2022-towards,
title = "Towards Need-Based Spoken Language Understanding Model Updates: What Have We Learned?",
author = "Do, Quynh and
Gaspers, Judith and
Sorokin, Daniil and
Lehnen, Patrick",
editor = "Li, Yunyao and
Lazaridou, Angeliki",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = dec,
year = "2022",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-industry.11",
doi = "10.18653/v1/2022.emnlp-industry.11",
pages = "121--127",
abstract = "In productionized machine learning systems, online model performance is known to deteriorate over time when there is a distributional drift between offline training and online application data. As a remedy, models are typically retrained at fixed time intervals, implying high computational and manual costs. This work aims at decreasing such costs in productionized, large-scale Spoken Language Understanding systems. In particular, we develop a need-based re-training strategy guided by an efficient drift detector and discuss the arising challenges including system complexity, overlapping model releases, observation limitation and the absence of annotated resources at runtime. We present empirical results on historical data and confirm the utility of our design decisions via an online A/B experiment.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="do-etal-2022-towards">
<titleInfo>
<title>Towards Need-Based Spoken Language Understanding Model Updates: What Have We Learned?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Quynh</namePart>
<namePart type="family">Do</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Daniil</namePart>
<namePart type="family">Sorokin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Lehnen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angeliki</namePart>
<namePart type="family">Lazaridou</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>In productionized machine learning systems, online model performance is known to deteriorate over time when there is a distributional drift between offline training and online application data. As a remedy, models are typically retrained at fixed time intervals, implying high computational and manual costs. This work aims at decreasing such costs in productionized, large-scale Spoken Language Understanding systems. In particular, we develop a need-based re-training strategy guided by an efficient drift detector and discuss the arising challenges including system complexity, overlapping model releases, observation limitation and the absence of annotated resources at runtime. We present empirical results on historical data and confirm the utility of our design decisions via an online A/B experiment.</abstract>
<identifier type="citekey">do-etal-2022-towards</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-industry.11</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-industry.11</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>121</start>
<end>127</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Need-Based Spoken Language Understanding Model Updates: What Have We Learned?
%A Do, Quynh
%A Gaspers, Judith
%A Sorokin, Daniil
%A Lehnen, Patrick
%Y Li, Yunyao
%Y Lazaridou, Angeliki
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F do-etal-2022-towards
%X In productionized machine learning systems, online model performance is known to deteriorate over time when there is a distributional drift between offline training and online application data. As a remedy, models are typically retrained at fixed time intervals, implying high computational and manual costs. This work aims at decreasing such costs in productionized, large-scale Spoken Language Understanding systems. In particular, we develop a need-based re-training strategy guided by an efficient drift detector and discuss the arising challenges including system complexity, overlapping model releases, observation limitation and the absence of annotated resources at runtime. We present empirical results on historical data and confirm the utility of our design decisions via an online A/B experiment.
%R 10.18653/v1/2022.emnlp-industry.11
%U https://aclanthology.org/2022.emnlp-industry.11
%U https://doi.org/10.18653/v1/2022.emnlp-industry.11
%P 121-127
Markdown (Informal)
[Towards Need-Based Spoken Language Understanding Model Updates: What Have We Learned?](https://aclanthology.org/2022.emnlp-industry.11) (Do et al., EMNLP 2022)
ACL