@inproceedings{mehrabani-etal-2018-practical,
title = "Practical Application of Domain Dependent Confidence Measurement for Spoken Language Understanding Systems",
author = "Mehrabani, Mahnoosh and
Thomson, David and
Stern, Benjamin",
editor = "Bangalore, Srinivas and
Chu-Carroll, Jennifer and
Li, Yunyao",
booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers)",
month = jun,
year = "2018",
address = "New Orleans - Louisiana",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N18-3023",
doi = "10.18653/v1/N18-3023",
pages = "185--192",
abstract = "Spoken Language Understanding (SLU), which extracts semantic information from speech, is not flawless, specially in practical applications. The reliability of the output of an SLU system can be evaluated using a semantic confidence measure. Confidence measures are a solution to improve the quality of spoken dialogue systems, by rejecting low-confidence SLU results. In this study we discuss real-world applications of confidence scoring in a customer service scenario. We build confidence models for three major types of dialogue states that are considered as different domains: how may I help you, number capture, and confirmation. Practical challenges to train domain-dependent confidence models, including data limitations, are discussed, and it is shown that feature engineering plays an important role to improve performance. We explore a wide variety of predictor features based on speech recognition, intent classification, and high-level domain knowledge, and find the combined feature set with the best rejection performance for each application.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mehrabani-etal-2018-practical">
<titleInfo>
<title>Practical Application of Domain Dependent Confidence Measurement for Spoken Language Understanding Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mahnoosh</namePart>
<namePart type="family">Mehrabani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Thomson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Stern</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Srinivas</namePart>
<namePart type="family">Bangalore</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="family">Chu-Carroll</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">New Orleans - Louisiana</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Spoken Language Understanding (SLU), which extracts semantic information from speech, is not flawless, specially in practical applications. The reliability of the output of an SLU system can be evaluated using a semantic confidence measure. Confidence measures are a solution to improve the quality of spoken dialogue systems, by rejecting low-confidence SLU results. In this study we discuss real-world applications of confidence scoring in a customer service scenario. We build confidence models for three major types of dialogue states that are considered as different domains: how may I help you, number capture, and confirmation. Practical challenges to train domain-dependent confidence models, including data limitations, are discussed, and it is shown that feature engineering plays an important role to improve performance. We explore a wide variety of predictor features based on speech recognition, intent classification, and high-level domain knowledge, and find the combined feature set with the best rejection performance for each application.</abstract>
<identifier type="citekey">mehrabani-etal-2018-practical</identifier>
<identifier type="doi">10.18653/v1/N18-3023</identifier>
<location>
<url>https://aclanthology.org/N18-3023</url>
</location>
<part>
<date>2018-06</date>
<extent unit="page">
<start>185</start>
<end>192</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Practical Application of Domain Dependent Confidence Measurement for Spoken Language Understanding Systems
%A Mehrabani, Mahnoosh
%A Thomson, David
%A Stern, Benjamin
%Y Bangalore, Srinivas
%Y Chu-Carroll, Jennifer
%Y Li, Yunyao
%S Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers)
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans - Louisiana
%F mehrabani-etal-2018-practical
%X Spoken Language Understanding (SLU), which extracts semantic information from speech, is not flawless, specially in practical applications. The reliability of the output of an SLU system can be evaluated using a semantic confidence measure. Confidence measures are a solution to improve the quality of spoken dialogue systems, by rejecting low-confidence SLU results. In this study we discuss real-world applications of confidence scoring in a customer service scenario. We build confidence models for three major types of dialogue states that are considered as different domains: how may I help you, number capture, and confirmation. Practical challenges to train domain-dependent confidence models, including data limitations, are discussed, and it is shown that feature engineering plays an important role to improve performance. We explore a wide variety of predictor features based on speech recognition, intent classification, and high-level domain knowledge, and find the combined feature set with the best rejection performance for each application.
%R 10.18653/v1/N18-3023
%U https://aclanthology.org/N18-3023
%U https://doi.org/10.18653/v1/N18-3023
%P 185-192
Markdown (Informal)
[Practical Application of Domain Dependent Confidence Measurement for Spoken Language Understanding Systems](https://aclanthology.org/N18-3023) (Mehrabani et al., NAACL 2018)
ACL