@inproceedings{dendukuri-etal-2021-using,
title = "Using Pause Information for More Accurate Entity Recognition",
author = "Dendukuri, Sahas and
Chitkara, Pooja and
Moniz, Joel Ruben Antony and
Yang, Xiao and
Tsagkias, Manos and
Pulman, Stephen",
editor = "Papangelis, Alexandros and
Budzianowski, Pawe{\l} and
Liu, Bing and
Nouri, Elnaz and
Rastogi, Abhinav and
Chen, Yun-Nung",
booktitle = "Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI",
month = nov,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.nlp4convai-1.22",
doi = "10.18653/v1/2021.nlp4convai-1.22",
pages = "243--250",
abstract = "Entity tags in human-machine dialog are integral to natural language understanding (NLU) tasks in conversational assistants. However, current systems struggle to accurately parse spoken queries with the typical use of text input alone, and often fail to understand the user intent. Previous work in linguistics has identified a cross-language tendency for longer speech pauses surrounding nouns as compared to verbs. We demonstrate that the linguistic observation on pauses can be used to improve accuracy in machine-learnt language understanding tasks. Analysis of pauses in French and English utterances from a commercial voice assistant shows the statistically significant difference in pause duration around multi-token entity span boundaries compared to within entity spans. Additionally, in contrast to text-based NLU, we apply pause duration to enrich contextual embeddings to improve shallow parsing of entities. Results show that our proposed novel embeddings improve the relative error rate by up to 8{\%} consistently across three domains for French, without any added annotation or alignment costs to the parser.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dendukuri-etal-2021-using">
<titleInfo>
<title>Using Pause Information for More Accurate Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sahas</namePart>
<namePart type="family">Dendukuri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pooja</namePart>
<namePart type="family">Chitkara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="given">Ruben</namePart>
<namePart type="given">Antony</namePart>
<namePart type="family">Moniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manos</namePart>
<namePart type="family">Tsagkias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Pulman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexandros</namePart>
<namePart type="family">Papangelis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paweł</namePart>
<namePart type="family">Budzianowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elnaz</namePart>
<namePart type="family">Nouri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Rastogi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Entity tags in human-machine dialog are integral to natural language understanding (NLU) tasks in conversational assistants. However, current systems struggle to accurately parse spoken queries with the typical use of text input alone, and often fail to understand the user intent. Previous work in linguistics has identified a cross-language tendency for longer speech pauses surrounding nouns as compared to verbs. We demonstrate that the linguistic observation on pauses can be used to improve accuracy in machine-learnt language understanding tasks. Analysis of pauses in French and English utterances from a commercial voice assistant shows the statistically significant difference in pause duration around multi-token entity span boundaries compared to within entity spans. Additionally, in contrast to text-based NLU, we apply pause duration to enrich contextual embeddings to improve shallow parsing of entities. Results show that our proposed novel embeddings improve the relative error rate by up to 8% consistently across three domains for French, without any added annotation or alignment costs to the parser.</abstract>
<identifier type="citekey">dendukuri-etal-2021-using</identifier>
<identifier type="doi">10.18653/v1/2021.nlp4convai-1.22</identifier>
<location>
<url>https://aclanthology.org/2021.nlp4convai-1.22</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>243</start>
<end>250</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using Pause Information for More Accurate Entity Recognition
%A Dendukuri, Sahas
%A Chitkara, Pooja
%A Moniz, Joel Ruben Antony
%A Yang, Xiao
%A Tsagkias, Manos
%A Pulman, Stephen
%Y Papangelis, Alexandros
%Y Budzianowski, Paweł
%Y Liu, Bing
%Y Nouri, Elnaz
%Y Rastogi, Abhinav
%Y Chen, Yun-Nung
%S Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online
%F dendukuri-etal-2021-using
%X Entity tags in human-machine dialog are integral to natural language understanding (NLU) tasks in conversational assistants. However, current systems struggle to accurately parse spoken queries with the typical use of text input alone, and often fail to understand the user intent. Previous work in linguistics has identified a cross-language tendency for longer speech pauses surrounding nouns as compared to verbs. We demonstrate that the linguistic observation on pauses can be used to improve accuracy in machine-learnt language understanding tasks. Analysis of pauses in French and English utterances from a commercial voice assistant shows the statistically significant difference in pause duration around multi-token entity span boundaries compared to within entity spans. Additionally, in contrast to text-based NLU, we apply pause duration to enrich contextual embeddings to improve shallow parsing of entities. Results show that our proposed novel embeddings improve the relative error rate by up to 8% consistently across three domains for French, without any added annotation or alignment costs to the parser.
%R 10.18653/v1/2021.nlp4convai-1.22
%U https://aclanthology.org/2021.nlp4convai-1.22
%U https://doi.org/10.18653/v1/2021.nlp4convai-1.22
%P 243-250
Markdown (Informal)
[Using Pause Information for More Accurate Entity Recognition](https://aclanthology.org/2021.nlp4convai-1.22) (Dendukuri et al., NLP4ConvAI 2021)
ACL
- Sahas Dendukuri, Pooja Chitkara, Joel Ruben Antony Moniz, Xiao Yang, Manos Tsagkias, and Stephen Pulman. 2021. Using Pause Information for More Accurate Entity Recognition. In Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI, pages 243–250, Online. Association for Computational Linguistics.