@inproceedings{belyi-etal-2023-personalized,
title = "Personalized Dense Retrieval on Global Index for Voice-enabled Conversational Systems",
author = "Belyi, Masha and
Dzialo, Charlotte and
Dwivedi, Chaitanya and
Muppidi, Prajit and
Shimizu, Kanna",
editor = "Wang, Mingxuan and
Zitouni, Imed",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-industry.9",
doi = "10.18653/v1/2023.emnlp-industry.9",
pages = "83--92",
abstract = "Voice-controlled AI dialogue systems are susceptible to noise from phonetic variations and failure to resolve ambiguous entities. Typically, personalized entity resolution (ER) and/or query rewrites (QR) are deployed to recover from these error modes. Previous work in this field achieves personalization by constraining retrieval search space to personalized indices built from user{'}s historical interactions with the device. While constrained retrieval achieves high precision, predictions are limited to entities in recent user history, which offers low coverage of future requests. Further, maintaining individual indices for millions of users is memory intensive and difficult to scale. In this work, we propose a personalized entity retrieval system that is robust to phonetic noise and ambiguity but is not limited to a personalized index. We achieve this by embedding user listening preferences into a contextual query embedding used in retrieval. We demonstrate our model{'}s ability to correct multiple error modes and show 91{\%} improvement over baseline on the entity retrieval task. Finally, we optimize the end-to-end approach to fit within online latency constraints while maintaining gains in performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="belyi-etal-2023-personalized">
<titleInfo>
<title>Personalized Dense Retrieval on Global Index for Voice-enabled Conversational Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Masha</namePart>
<namePart type="family">Belyi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charlotte</namePart>
<namePart type="family">Dzialo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chaitanya</namePart>
<namePart type="family">Dwivedi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prajit</namePart>
<namePart type="family">Muppidi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kanna</namePart>
<namePart type="family">Shimizu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mingxuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Voice-controlled AI dialogue systems are susceptible to noise from phonetic variations and failure to resolve ambiguous entities. Typically, personalized entity resolution (ER) and/or query rewrites (QR) are deployed to recover from these error modes. Previous work in this field achieves personalization by constraining retrieval search space to personalized indices built from user’s historical interactions with the device. While constrained retrieval achieves high precision, predictions are limited to entities in recent user history, which offers low coverage of future requests. Further, maintaining individual indices for millions of users is memory intensive and difficult to scale. In this work, we propose a personalized entity retrieval system that is robust to phonetic noise and ambiguity but is not limited to a personalized index. We achieve this by embedding user listening preferences into a contextual query embedding used in retrieval. We demonstrate our model’s ability to correct multiple error modes and show 91% improvement over baseline on the entity retrieval task. Finally, we optimize the end-to-end approach to fit within online latency constraints while maintaining gains in performance.</abstract>
<identifier type="citekey">belyi-etal-2023-personalized</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-industry.9</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-industry.9</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>83</start>
<end>92</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Personalized Dense Retrieval on Global Index for Voice-enabled Conversational Systems
%A Belyi, Masha
%A Dzialo, Charlotte
%A Dwivedi, Chaitanya
%A Muppidi, Prajit
%A Shimizu, Kanna
%Y Wang, Mingxuan
%Y Zitouni, Imed
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F belyi-etal-2023-personalized
%X Voice-controlled AI dialogue systems are susceptible to noise from phonetic variations and failure to resolve ambiguous entities. Typically, personalized entity resolution (ER) and/or query rewrites (QR) are deployed to recover from these error modes. Previous work in this field achieves personalization by constraining retrieval search space to personalized indices built from user’s historical interactions with the device. While constrained retrieval achieves high precision, predictions are limited to entities in recent user history, which offers low coverage of future requests. Further, maintaining individual indices for millions of users is memory intensive and difficult to scale. In this work, we propose a personalized entity retrieval system that is robust to phonetic noise and ambiguity but is not limited to a personalized index. We achieve this by embedding user listening preferences into a contextual query embedding used in retrieval. We demonstrate our model’s ability to correct multiple error modes and show 91% improvement over baseline on the entity retrieval task. Finally, we optimize the end-to-end approach to fit within online latency constraints while maintaining gains in performance.
%R 10.18653/v1/2023.emnlp-industry.9
%U https://aclanthology.org/2023.emnlp-industry.9
%U https://doi.org/10.18653/v1/2023.emnlp-industry.9
%P 83-92
Markdown (Informal)
[Personalized Dense Retrieval on Global Index for Voice-enabled Conversational Systems](https://aclanthology.org/2023.emnlp-industry.9) (Belyi et al., EMNLP 2023)
ACL