@inproceedings{nguyen-yu-2021-improving,
title = "Improving Named Entity Recognition in Spoken Dialog Systems by Context and Speech Pattern Modeling",
author = "Nguyen, Minh and
Yu, Zhou",
editor = "Li, Haizhou and
Levow, Gina-Anne and
Yu, Zhou and
Gupta, Chitralekha and
Sisman, Berrak and
Cai, Siqi and
Vandyke, David and
Dethlefs, Nina and
Wu, Yan and
Li, Junyi Jessy",
booktitle = "Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = jul,
year = "2021",
address = "Singapore and Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.sigdial-1.6",
doi = "10.18653/v1/2021.sigdial-1.6",
pages = "45--55",
abstract = "While named entity recognition (NER) from speech has been around as long as NER from written text has, the accuracy of NER from speech has generally been much lower than that of NER from text. The rise in popularity of spoken dialog systems such as Siri or Alexa highlights the need for more accurate NER from speech because NER is a core component for understanding what users said in dialogs. Deployed spoken dialog systems receive user input in the form of automatic speech recognition (ASR) transcripts, and simply applying NER model trained on written text to ASR transcripts often leads to low accuracy because compared to written text, ASR transcripts lack important cues such as punctuation and capitalization. Besides, errors in ASR transcripts also make NER from speech challenging. We propose two models that exploit dialog context and speech pattern clues to extract named entities more accurately from open-domain dialogs in spoken dialog systems. Our results show the benefit of modeling dialog context and speech patterns in two settings: a standard setting with random partition of data and a more realistic but also more difficult setting where many named entities encountered during deployment are unseen during training.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-yu-2021-improving">
<titleInfo>
<title>Improving Named Entity Recognition in Spoken Dialog Systems by Context and Speech Pattern Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Minh</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haizhou</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gina-Anne</namePart>
<namePart type="family">Levow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chitralekha</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Berrak</namePart>
<namePart type="family">Sisman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siqi</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Vandyke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nina</namePart>
<namePart type="family">Dethlefs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="given">Jessy</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">Singapore and Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While named entity recognition (NER) from speech has been around as long as NER from written text has, the accuracy of NER from speech has generally been much lower than that of NER from text. The rise in popularity of spoken dialog systems such as Siri or Alexa highlights the need for more accurate NER from speech because NER is a core component for understanding what users said in dialogs. Deployed spoken dialog systems receive user input in the form of automatic speech recognition (ASR) transcripts, and simply applying NER model trained on written text to ASR transcripts often leads to low accuracy because compared to written text, ASR transcripts lack important cues such as punctuation and capitalization. Besides, errors in ASR transcripts also make NER from speech challenging. We propose two models that exploit dialog context and speech pattern clues to extract named entities more accurately from open-domain dialogs in spoken dialog systems. Our results show the benefit of modeling dialog context and speech patterns in two settings: a standard setting with random partition of data and a more realistic but also more difficult setting where many named entities encountered during deployment are unseen during training.</abstract>
<identifier type="citekey">nguyen-yu-2021-improving</identifier>
<identifier type="doi">10.18653/v1/2021.sigdial-1.6</identifier>
<location>
<url>https://aclanthology.org/2021.sigdial-1.6</url>
</location>
<part>
<date>2021-07</date>
<extent unit="page">
<start>45</start>
<end>55</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Named Entity Recognition in Spoken Dialog Systems by Context and Speech Pattern Modeling
%A Nguyen, Minh
%A Yu, Zhou
%Y Li, Haizhou
%Y Levow, Gina-Anne
%Y Yu, Zhou
%Y Gupta, Chitralekha
%Y Sisman, Berrak
%Y Cai, Siqi
%Y Vandyke, David
%Y Dethlefs, Nina
%Y Wu, Yan
%Y Li, Junyi Jessy
%S Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2021
%8 July
%I Association for Computational Linguistics
%C Singapore and Online
%F nguyen-yu-2021-improving
%X While named entity recognition (NER) from speech has been around as long as NER from written text has, the accuracy of NER from speech has generally been much lower than that of NER from text. The rise in popularity of spoken dialog systems such as Siri or Alexa highlights the need for more accurate NER from speech because NER is a core component for understanding what users said in dialogs. Deployed spoken dialog systems receive user input in the form of automatic speech recognition (ASR) transcripts, and simply applying NER model trained on written text to ASR transcripts often leads to low accuracy because compared to written text, ASR transcripts lack important cues such as punctuation and capitalization. Besides, errors in ASR transcripts also make NER from speech challenging. We propose two models that exploit dialog context and speech pattern clues to extract named entities more accurately from open-domain dialogs in spoken dialog systems. Our results show the benefit of modeling dialog context and speech patterns in two settings: a standard setting with random partition of data and a more realistic but also more difficult setting where many named entities encountered during deployment are unseen during training.
%R 10.18653/v1/2021.sigdial-1.6
%U https://aclanthology.org/2021.sigdial-1.6
%U https://doi.org/10.18653/v1/2021.sigdial-1.6
%P 45-55
Markdown (Informal)
[Improving Named Entity Recognition in Spoken Dialog Systems by Context and Speech Pattern Modeling](https://aclanthology.org/2021.sigdial-1.6) (Nguyen & Yu, SIGDIAL 2021)
ACL