@inproceedings{alam-etal-2021-new,
title = "New Domain, Major Effort? How Much Data is Necessary to Adapt a Temporal Tagger to the Voice Assistant Domain",
author = "Alam, Touhidul and
Zarcone, Alessandra and
Pad{\'o}, Sebastian",
editor = "Zarrie{\ss}, Sina and
Bos, Johan and
van Noord, Rik and
Abzianidze, Lasha",
booktitle = "Proceedings of the 14th International Conference on Computational Semantics (IWCS)",
month = jun,
year = "2021",
address = "Groningen, The Netherlands (online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.iwcs-1.14",
pages = "144--154",
abstract = "Reliable tagging of Temporal Expressions (TEs, e.g., Book a table at L{'}Osteria for Sunday evening) is a central requirement for Voice Assistants (VAs). However, there is a dearth of resources and systems for the VA domain, since publicly-available temporal taggers are trained only on substantially different domains, such as news and clinical text. Since the cost of annotating large datasets is prohibitive, we investigate the trade-off between in-domain data and performance in DA-Time, a hybrid temporal tagger for the English VA domain which combines a neural architecture for robust TE recognition, with a parser-based TE normalizer. We find that transfer learning goes a long way even with as little as 25 in-domain sentences: DA-Time performs at the state of the art on the news domain, and substantially outperforms it on the VA domain.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alam-etal-2021-new">
<titleInfo>
<title>New Domain, Major Effort? How Much Data is Necessary to Adapt a Temporal Tagger to the Voice Assistant Domain</title>
</titleInfo>
<name type="personal">
<namePart type="given">Touhidul</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandra</namePart>
<namePart type="family">Zarcone</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Padó</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 14th International Conference on Computational Semantics (IWCS)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Zarrieß</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johan</namePart>
<namePart type="family">Bos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rik</namePart>
<namePart type="family">van Noord</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lasha</namePart>
<namePart type="family">Abzianidze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Groningen, The Netherlands (online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Reliable tagging of Temporal Expressions (TEs, e.g., Book a table at L’Osteria for Sunday evening) is a central requirement for Voice Assistants (VAs). However, there is a dearth of resources and systems for the VA domain, since publicly-available temporal taggers are trained only on substantially different domains, such as news and clinical text. Since the cost of annotating large datasets is prohibitive, we investigate the trade-off between in-domain data and performance in DA-Time, a hybrid temporal tagger for the English VA domain which combines a neural architecture for robust TE recognition, with a parser-based TE normalizer. We find that transfer learning goes a long way even with as little as 25 in-domain sentences: DA-Time performs at the state of the art on the news domain, and substantially outperforms it on the VA domain.</abstract>
<identifier type="citekey">alam-etal-2021-new</identifier>
<location>
<url>https://aclanthology.org/2021.iwcs-1.14</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>144</start>
<end>154</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T New Domain, Major Effort? How Much Data is Necessary to Adapt a Temporal Tagger to the Voice Assistant Domain
%A Alam, Touhidul
%A Zarcone, Alessandra
%A Padó, Sebastian
%Y Zarrieß, Sina
%Y Bos, Johan
%Y van Noord, Rik
%Y Abzianidze, Lasha
%S Proceedings of the 14th International Conference on Computational Semantics (IWCS)
%D 2021
%8 June
%I Association for Computational Linguistics
%C Groningen, The Netherlands (online)
%F alam-etal-2021-new
%X Reliable tagging of Temporal Expressions (TEs, e.g., Book a table at L’Osteria for Sunday evening) is a central requirement for Voice Assistants (VAs). However, there is a dearth of resources and systems for the VA domain, since publicly-available temporal taggers are trained only on substantially different domains, such as news and clinical text. Since the cost of annotating large datasets is prohibitive, we investigate the trade-off between in-domain data and performance in DA-Time, a hybrid temporal tagger for the English VA domain which combines a neural architecture for robust TE recognition, with a parser-based TE normalizer. We find that transfer learning goes a long way even with as little as 25 in-domain sentences: DA-Time performs at the state of the art on the news domain, and substantially outperforms it on the VA domain.
%U https://aclanthology.org/2021.iwcs-1.14
%P 144-154
Markdown (Informal)
[New Domain, Major Effort? How Much Data is Necessary to Adapt a Temporal Tagger to the Voice Assistant Domain](https://aclanthology.org/2021.iwcs-1.14) (Alam et al., IWCS 2021)
ACL