@inproceedings{maclaughlin-etal-2020-evaluating,
title = "Evaluating the Effectiveness of Efficient Neural Architecture Search for Sentence-Pair Tasks",
author = "MacLaughlin, Ansel and
Dhamala, Jwala and
Kumar, Anoop and
Venkatapathy, Sriram and
Venkatesan, Ragav and
Gupta, Rahul",
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-1.4",
doi = "10.18653/v1/2020.insights-1.4",
pages = "22--31",
abstract = "Neural Architecture Search (NAS) methods, which automatically learn entire neural model or individual neural cell architectures, have recently achieved competitive or state-of-the-art (SOTA) performance on variety of natural language processing and computer vision tasks, including language modeling, natural language inference, and image classification. In this work, we explore the applicability of a SOTA NAS algorithm, Efficient Neural Architecture Search (ENAS) (Pham et al., 2018) to two sentence pair tasks, paraphrase detection and semantic textual similarity. We use ENAS to perform a micro-level search and learn a task-optimized RNN cell architecture as a drop-in replacement for an LSTM. We explore the effectiveness of ENAS through experiments on three datasets (MRPC, SICK, STS-B), with two different models (ESIM, BiLSTM-Max), and two sets of embeddings (Glove, BERT). In contrast to prior work applying ENAS to NLP tasks, our results are mixed {--} we find that ENAS architectures sometimes, but not always, outperform LSTMs and perform similarly to random architecture search.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maclaughlin-etal-2020-evaluating">
<titleInfo>
<title>Evaluating the Effectiveness of Efficient Neural Architecture Search for Sentence-Pair Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ansel</namePart>
<namePart type="family">MacLaughlin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jwala</namePart>
<namePart type="family">Dhamala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Kumar</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">Ragav</namePart>
<namePart type="family">Venkatesan</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>
<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 Architecture Search (NAS) methods, which automatically learn entire neural model or individual neural cell architectures, have recently achieved competitive or state-of-the-art (SOTA) performance on variety of natural language processing and computer vision tasks, including language modeling, natural language inference, and image classification. In this work, we explore the applicability of a SOTA NAS algorithm, Efficient Neural Architecture Search (ENAS) (Pham et al., 2018) to two sentence pair tasks, paraphrase detection and semantic textual similarity. We use ENAS to perform a micro-level search and learn a task-optimized RNN cell architecture as a drop-in replacement for an LSTM. We explore the effectiveness of ENAS through experiments on three datasets (MRPC, SICK, STS-B), with two different models (ESIM, BiLSTM-Max), and two sets of embeddings (Glove, BERT). In contrast to prior work applying ENAS to NLP tasks, our results are mixed – we find that ENAS architectures sometimes, but not always, outperform LSTMs and perform similarly to random architecture search.</abstract>
<identifier type="citekey">maclaughlin-etal-2020-evaluating</identifier>
<identifier type="doi">10.18653/v1/2020.insights-1.4</identifier>
<location>
<url>https://aclanthology.org/2020.insights-1.4</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>22</start>
<end>31</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating the Effectiveness of Efficient Neural Architecture Search for Sentence-Pair Tasks
%A MacLaughlin, Ansel
%A Dhamala, Jwala
%A Kumar, Anoop
%A Venkatapathy, Sriram
%A Venkatesan, Ragav
%A Gupta, Rahul
%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 maclaughlin-etal-2020-evaluating
%X Neural Architecture Search (NAS) methods, which automatically learn entire neural model or individual neural cell architectures, have recently achieved competitive or state-of-the-art (SOTA) performance on variety of natural language processing and computer vision tasks, including language modeling, natural language inference, and image classification. In this work, we explore the applicability of a SOTA NAS algorithm, Efficient Neural Architecture Search (ENAS) (Pham et al., 2018) to two sentence pair tasks, paraphrase detection and semantic textual similarity. We use ENAS to perform a micro-level search and learn a task-optimized RNN cell architecture as a drop-in replacement for an LSTM. We explore the effectiveness of ENAS through experiments on three datasets (MRPC, SICK, STS-B), with two different models (ESIM, BiLSTM-Max), and two sets of embeddings (Glove, BERT). In contrast to prior work applying ENAS to NLP tasks, our results are mixed – we find that ENAS architectures sometimes, but not always, outperform LSTMs and perform similarly to random architecture search.
%R 10.18653/v1/2020.insights-1.4
%U https://aclanthology.org/2020.insights-1.4
%U https://doi.org/10.18653/v1/2020.insights-1.4
%P 22-31
Markdown (Informal)
[Evaluating the Effectiveness of Efficient Neural Architecture Search for Sentence-Pair Tasks](https://aclanthology.org/2020.insights-1.4) (MacLaughlin et al., insights 2020)
ACL