@inproceedings{zupon-etal-2020-analysis,
title = "An Analysis of Capsule Networks for Part of Speech Tagging in High- and Low-resource Scenarios",
author = "Zupon, Andrew and
Rafique, Faiz and
Surdeanu, Mihai",
editor = "Rogers, Anna and
Sedoc, Jo{\~a}o and
Rumshisky, Anna",
booktitle = "Proceedings of the First Workshop on Insights from Negative Results in NLP",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.insights-1.10",
doi = "10.18653/v1/2020.insights-1.10",
pages = "66--70",
abstract = "Neural networks are a common tool in NLP, but it is not always clear which architecture to use for a given task. Different tasks, different languages, and different training conditions can all affect how a neural network will perform. Capsule Networks (CapsNets) are a relatively new architecture in NLP. Due to their novelty, CapsNets are being used more and more in NLP tasks. However, their usefulness is still mostly untested. In this paper, we compare three neural network architectures{---}LSTM, CNN, and CapsNet{---}on a part of speech tagging task. We compare these architectures in both high- and low-resource training conditions and find that no architecture consistently performs the best. Our analysis shows that our CapsNet performs nearly as well as a more complex LSTM under certain training conditions, but not others, and that our CapsNet almost always outperforms our CNN. We also find that our CapsNet implementation shows faster prediction times than the LSTM for Scottish Gaelic but not for Spanish, highlighting the effect that the choice of languages can have on the models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zupon-etal-2020-analysis">
<titleInfo>
<title>An Analysis of Capsule Networks for Part of Speech Tagging in High- and Low-resource Scenarios</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Zupon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Faiz</namePart>
<namePart type="family">Rafique</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihai</namePart>
<namePart type="family">Surdeanu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Insights from Negative Results in NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</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>Neural networks are a common tool in NLP, but it is not always clear which architecture to use for a given task. Different tasks, different languages, and different training conditions can all affect how a neural network will perform. Capsule Networks (CapsNets) are a relatively new architecture in NLP. Due to their novelty, CapsNets are being used more and more in NLP tasks. However, their usefulness is still mostly untested. In this paper, we compare three neural network architectures—LSTM, CNN, and CapsNet—on a part of speech tagging task. We compare these architectures in both high- and low-resource training conditions and find that no architecture consistently performs the best. Our analysis shows that our CapsNet performs nearly as well as a more complex LSTM under certain training conditions, but not others, and that our CapsNet almost always outperforms our CNN. We also find that our CapsNet implementation shows faster prediction times than the LSTM for Scottish Gaelic but not for Spanish, highlighting the effect that the choice of languages can have on the models.</abstract>
<identifier type="citekey">zupon-etal-2020-analysis</identifier>
<identifier type="doi">10.18653/v1/2020.insights-1.10</identifier>
<location>
<url>https://aclanthology.org/2020.insights-1.10</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>66</start>
<end>70</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Analysis of Capsule Networks for Part of Speech Tagging in High- and Low-resource Scenarios
%A Zupon, Andrew
%A Rafique, Faiz
%A Surdeanu, Mihai
%Y Rogers, Anna
%Y Sedoc, João
%Y Rumshisky, Anna
%S Proceedings of the First Workshop on Insights from Negative Results in NLP
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F zupon-etal-2020-analysis
%X Neural networks are a common tool in NLP, but it is not always clear which architecture to use for a given task. Different tasks, different languages, and different training conditions can all affect how a neural network will perform. Capsule Networks (CapsNets) are a relatively new architecture in NLP. Due to their novelty, CapsNets are being used more and more in NLP tasks. However, their usefulness is still mostly untested. In this paper, we compare three neural network architectures—LSTM, CNN, and CapsNet—on a part of speech tagging task. We compare these architectures in both high- and low-resource training conditions and find that no architecture consistently performs the best. Our analysis shows that our CapsNet performs nearly as well as a more complex LSTM under certain training conditions, but not others, and that our CapsNet almost always outperforms our CNN. We also find that our CapsNet implementation shows faster prediction times than the LSTM for Scottish Gaelic but not for Spanish, highlighting the effect that the choice of languages can have on the models.
%R 10.18653/v1/2020.insights-1.10
%U https://aclanthology.org/2020.insights-1.10
%U https://doi.org/10.18653/v1/2020.insights-1.10
%P 66-70
Markdown (Informal)
[An Analysis of Capsule Networks for Part of Speech Tagging in High- and Low-resource Scenarios](https://aclanthology.org/2020.insights-1.10) (Zupon et al., insights 2020)
ACL