@inproceedings{trajanovski-etal-2021-text,
title = "When does text prediction benefit from additional context? An exploration of contextual signals for chat and email messages",
author = "Trajanovski, Stojan and
Atalla, Chad and
Kim, Kunho and
Agarwal, Vipul and
Shokouhi, Milad and
Quirk, Chris",
editor = "Kim, Young-bum and
Li, Yunyao and
Rambow, Owen",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-industry.1",
doi = "10.18653/v1/2021.naacl-industry.1",
pages = "1--9",
abstract = "Email and chat communication tools are increasingly important for completing daily tasks. Accurate real-time phrase completion can save time and bolster productivity. Modern text prediction algorithms are based on large language models which typically rely on the prior words in a message to predict a completion. We examine how additional contextual signals (from previous messages, time, and subject) affect the performance of a commercial text prediction model. We compare contextual text prediction in chat and email messages from two of the largest commercial platforms Microsoft Teams and Outlook, finding that contextual signals contribute to performance differently between these scenarios. On emails, time context is most beneficial with small relative gains of 2{\%} over baseline. Whereas, in chat scenarios, using a tailored set of previous messages as context yields relative improvements over the baseline between 9.3{\%} and 18.6{\%} across various critical service-oriented text prediction metrics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="trajanovski-etal-2021-text">
<titleInfo>
<title>When does text prediction benefit from additional context? An exploration of contextual signals for chat and email messages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stojan</namePart>
<namePart type="family">Trajanovski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chad</namePart>
<namePart type="family">Atalla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kunho</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vipul</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Milad</namePart>
<namePart type="family">Shokouhi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Quirk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Young-bum</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Owen</namePart>
<namePart type="family">Rambow</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>Email and chat communication tools are increasingly important for completing daily tasks. Accurate real-time phrase completion can save time and bolster productivity. Modern text prediction algorithms are based on large language models which typically rely on the prior words in a message to predict a completion. We examine how additional contextual signals (from previous messages, time, and subject) affect the performance of a commercial text prediction model. We compare contextual text prediction in chat and email messages from two of the largest commercial platforms Microsoft Teams and Outlook, finding that contextual signals contribute to performance differently between these scenarios. On emails, time context is most beneficial with small relative gains of 2% over baseline. Whereas, in chat scenarios, using a tailored set of previous messages as context yields relative improvements over the baseline between 9.3% and 18.6% across various critical service-oriented text prediction metrics.</abstract>
<identifier type="citekey">trajanovski-etal-2021-text</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-industry.1</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-industry.1</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>1</start>
<end>9</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When does text prediction benefit from additional context? An exploration of contextual signals for chat and email messages
%A Trajanovski, Stojan
%A Atalla, Chad
%A Kim, Kunho
%A Agarwal, Vipul
%A Shokouhi, Milad
%A Quirk, Chris
%Y Kim, Young-bum
%Y Li, Yunyao
%Y Rambow, Owen
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F trajanovski-etal-2021-text
%X Email and chat communication tools are increasingly important for completing daily tasks. Accurate real-time phrase completion can save time and bolster productivity. Modern text prediction algorithms are based on large language models which typically rely on the prior words in a message to predict a completion. We examine how additional contextual signals (from previous messages, time, and subject) affect the performance of a commercial text prediction model. We compare contextual text prediction in chat and email messages from two of the largest commercial platforms Microsoft Teams and Outlook, finding that contextual signals contribute to performance differently between these scenarios. On emails, time context is most beneficial with small relative gains of 2% over baseline. Whereas, in chat scenarios, using a tailored set of previous messages as context yields relative improvements over the baseline between 9.3% and 18.6% across various critical service-oriented text prediction metrics.
%R 10.18653/v1/2021.naacl-industry.1
%U https://aclanthology.org/2021.naacl-industry.1
%U https://doi.org/10.18653/v1/2021.naacl-industry.1
%P 1-9
Markdown (Informal)
[When does text prediction benefit from additional context? An exploration of contextual signals for chat and email messages](https://aclanthology.org/2021.naacl-industry.1) (Trajanovski et al., NAACL 2021)
ACL