@inproceedings{schroedl-etal-2022-improving,
title = "Improving Large-Scale Conversational Assistants using Model Interpretation based Training Sample Selection",
author = "Schroedl, Stefan and
Kumar, Manoj and
Hajebi, Kiana and
Ziyadi, Morteza and
Venkatapathy, Sriram and
Ramakrishna, Anil and
Gupta, Rahul and
Natarajan, Pradeep",
editor = "Li, Yunyao and
Lazaridou, Angeliki",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = dec,
year = "2022",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-industry.37",
doi = "10.18653/v1/2022.emnlp-industry.37",
pages = "371--378",
abstract = "This paper presents an approach to identify samples from live traffic where the customer implicitly communicated satisfaction with Alexa{'}s responses, by leveraging interpretations of model behavior. Such customer signals are noisy and adding a large number of samples from live traffic to training set makes re-training infeasible. Our work addresses these challenges by identifying a small number of samples that grow training set by {\textasciitilde}0.05{\%} while producing statistically significant improvements in both offline and online tests.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schroedl-etal-2022-improving">
<titleInfo>
<title>Improving Large-Scale Conversational Assistants using Model Interpretation based Training Sample Selection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Schroedl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manoj</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kiana</namePart>
<namePart type="family">Hajebi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Morteza</namePart>
<namePart type="family">Ziyadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sriram</namePart>
<namePart type="family">Venkatapathy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anil</namePart>
<namePart type="family">Ramakrishna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pradeep</namePart>
<namePart type="family">Natarajan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angeliki</namePart>
<namePart type="family">Lazaridou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents an approach to identify samples from live traffic where the customer implicitly communicated satisfaction with Alexa’s responses, by leveraging interpretations of model behavior. Such customer signals are noisy and adding a large number of samples from live traffic to training set makes re-training infeasible. Our work addresses these challenges by identifying a small number of samples that grow training set by ~0.05% while producing statistically significant improvements in both offline and online tests.</abstract>
<identifier type="citekey">schroedl-etal-2022-improving</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-industry.37</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-industry.37</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>371</start>
<end>378</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Large-Scale Conversational Assistants using Model Interpretation based Training Sample Selection
%A Schroedl, Stefan
%A Kumar, Manoj
%A Hajebi, Kiana
%A Ziyadi, Morteza
%A Venkatapathy, Sriram
%A Ramakrishna, Anil
%A Gupta, Rahul
%A Natarajan, Pradeep
%Y Li, Yunyao
%Y Lazaridou, Angeliki
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F schroedl-etal-2022-improving
%X This paper presents an approach to identify samples from live traffic where the customer implicitly communicated satisfaction with Alexa’s responses, by leveraging interpretations of model behavior. Such customer signals are noisy and adding a large number of samples from live traffic to training set makes re-training infeasible. Our work addresses these challenges by identifying a small number of samples that grow training set by ~0.05% while producing statistically significant improvements in both offline and online tests.
%R 10.18653/v1/2022.emnlp-industry.37
%U https://aclanthology.org/2022.emnlp-industry.37
%U https://doi.org/10.18653/v1/2022.emnlp-industry.37
%P 371-378
Markdown (Informal)
[Improving Large-Scale Conversational Assistants using Model Interpretation based Training Sample Selection](https://aclanthology.org/2022.emnlp-industry.37) (Schroedl et al., EMNLP 2022)
ACL
- Stefan Schroedl, Manoj Kumar, Kiana Hajebi, Morteza Ziyadi, Sriram Venkatapathy, Anil Ramakrishna, Rahul Gupta, and Pradeep Natarajan. 2022. Improving Large-Scale Conversational Assistants using Model Interpretation based Training Sample Selection. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 371–378, Abu Dhabi, UAE. Association for Computational Linguistics.