@inproceedings{raghuvanshi-etal-2019-entity,
title = "Entity resolution for noisy {ASR} transcripts",
author = "Raghuvanshi, Arushi and
Ramakrishnan, Vijay and
Embar, Varsha and
Carroll, Lucien and
Raghunathan, Karthik",
editor = "Pad{\'o}, Sebastian and
Huang, Ruihong",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): System Demonstrations",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-3011",
doi = "10.18653/v1/D19-3011",
pages = "61--66",
abstract = "Large vocabulary domain-agnostic Automatic Speech Recognition (ASR) systems often mistranscribe domain-specific words and phrases. Since these generic ASR systems are the first component of most voice assistants in production, building Natural Language Understanding (NLU) systems that are robust to these errors can be a challenging task. In this paper, we focus on handling ASR errors in named entities, specifically person names, for a voice-based collaboration assistant. We demonstrate an effective method for resolving person names that are mistranscribed by black-box ASR systems, using character and phoneme-based information retrieval techniques and contextual information, which improves accuracy by 40.8{\%} on our production system. We provide a live interactive demo to further illustrate the nuances of this problem and the effectiveness of our solution.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="raghuvanshi-etal-2019-entity">
<titleInfo>
<title>Entity resolution for noisy ASR transcripts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arushi</namePart>
<namePart type="family">Raghuvanshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vijay</namePart>
<namePart type="family">Ramakrishnan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varsha</namePart>
<namePart type="family">Embar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucien</namePart>
<namePart type="family">Carroll</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karthik</namePart>
<namePart type="family">Raghunathan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Padó</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruihong</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large vocabulary domain-agnostic Automatic Speech Recognition (ASR) systems often mistranscribe domain-specific words and phrases. Since these generic ASR systems are the first component of most voice assistants in production, building Natural Language Understanding (NLU) systems that are robust to these errors can be a challenging task. In this paper, we focus on handling ASR errors in named entities, specifically person names, for a voice-based collaboration assistant. We demonstrate an effective method for resolving person names that are mistranscribed by black-box ASR systems, using character and phoneme-based information retrieval techniques and contextual information, which improves accuracy by 40.8% on our production system. We provide a live interactive demo to further illustrate the nuances of this problem and the effectiveness of our solution.</abstract>
<identifier type="citekey">raghuvanshi-etal-2019-entity</identifier>
<identifier type="doi">10.18653/v1/D19-3011</identifier>
<location>
<url>https://aclanthology.org/D19-3011</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>61</start>
<end>66</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Entity resolution for noisy ASR transcripts
%A Raghuvanshi, Arushi
%A Ramakrishnan, Vijay
%A Embar, Varsha
%A Carroll, Lucien
%A Raghunathan, Karthik
%Y Padó, Sebastian
%Y Huang, Ruihong
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): System Demonstrations
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F raghuvanshi-etal-2019-entity
%X Large vocabulary domain-agnostic Automatic Speech Recognition (ASR) systems often mistranscribe domain-specific words and phrases. Since these generic ASR systems are the first component of most voice assistants in production, building Natural Language Understanding (NLU) systems that are robust to these errors can be a challenging task. In this paper, we focus on handling ASR errors in named entities, specifically person names, for a voice-based collaboration assistant. We demonstrate an effective method for resolving person names that are mistranscribed by black-box ASR systems, using character and phoneme-based information retrieval techniques and contextual information, which improves accuracy by 40.8% on our production system. We provide a live interactive demo to further illustrate the nuances of this problem and the effectiveness of our solution.
%R 10.18653/v1/D19-3011
%U https://aclanthology.org/D19-3011
%U https://doi.org/10.18653/v1/D19-3011
%P 61-66
Markdown (Informal)
[Entity resolution for noisy ASR transcripts](https://aclanthology.org/D19-3011) (Raghuvanshi et al., EMNLP-IJCNLP 2019)
ACL
- Arushi Raghuvanshi, Vijay Ramakrishnan, Varsha Embar, Lucien Carroll, and Karthik Raghunathan. 2019. Entity resolution for noisy ASR transcripts. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): System Demonstrations, pages 61–66, Hong Kong, China. Association for Computational Linguistics.