Characterizing the hyper-parameter space of LSTM language models for mixed context applications

Applying state of the art deep learning models to novel real world datasets gives a practical evaluation of the generalizability of these models. Of importance in this process is how sensitive the hyper parameters of such models are to novel datasets as this would affect the reproducibility of a mod...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Akinwande, Victor, Remy, Sekou L
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computation and Language
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

container_end_page
container_issue
container_start_page
container_title
container_volume
creator	Akinwande, Victor Remy, Sekou L
description	Applying state of the art deep learning models to novel real world datasets gives a practical evaluation of the generalizability of these models. Of importance in this process is how sensitive the hyper parameters of such models are to novel datasets as this would affect the reproducibility of a model. We present work to characterize the hyper parameter space of an LSTM for language modeling on a code-mixed corpus. We observe that the evaluated model shows minimal sensitivity to our novel dataset bar a few hyper parameters.
doi_str_mv	10.48550/arxiv.1712.03199
format	Article
fullrecord	<record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1712_03199</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1712_03199</sourcerecordid><originalsourceid>FETCH-LOGICAL-a679-6b23eca9065f016325dce00da57b970c56f7b90f82f7000a8146e4ff78de070e3</originalsourceid><addsrcrecordid>eNotj81OhDAUhbtxYUYfwJV9AfAWaAtLQ_xLMLOQPblTbqEJP01Bw_j04ujqnJwvOcnH2J2AOMulhAcMm_uKhRZJDKkoimvWlD0GNCsF9-2mjq898f7sKUR-30faAV88GuKz5dVH_c4HnLpP7IiPc0vDwu0c-Og2armZp5W2laP3gzO4unlabtiVxWGh2_88sPr5qS5fo-r48lY-VhEqXUTqlKRksAAlLQiVJrI1BNCi1KdCg5HK7gVsnlgNAJiLTFFmrc5bAg2UHtj93-3FsPHBjRjOza9pczFNfwDXa09z</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Characterizing the hyper-parameter space of LSTM language models for mixed context applications</title><source>arXiv.org</source><creator>Akinwande, Victor ; Remy, Sekou L</creator><creatorcontrib>Akinwande, Victor ; Remy, Sekou L</creatorcontrib><description>Applying state of the art deep learning models to novel real world datasets gives a practical evaluation of the generalizability of these models. Of importance in this process is how sensitive the hyper parameters of such models are to novel datasets as this would affect the reproducibility of a model. We present work to characterize the hyper parameter space of an LSTM for language modeling on a code-mixed corpus. We observe that the evaluated model shows minimal sensitivity to our novel dataset bar a few hyper parameters.</description><identifier>DOI: 10.48550/arxiv.1712.03199</identifier><language>eng</language><subject>Computer Science - Computation and Language</subject><creationdate>2017-12</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,782,887</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1712.03199$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1712.03199$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Akinwande, Victor</creatorcontrib><creatorcontrib>Remy, Sekou L</creatorcontrib><title>Characterizing the hyper-parameter space of LSTM language models for mixed context applications</title><description>Applying state of the art deep learning models to novel real world datasets gives a practical evaluation of the generalizability of these models. Of importance in this process is how sensitive the hyper parameters of such models are to novel datasets as this would affect the reproducibility of a model. We present work to characterize the hyper parameter space of an LSTM for language modeling on a code-mixed corpus. We observe that the evaluated model shows minimal sensitivity to our novel dataset bar a few hyper parameters.</description><subject>Computer Science - Computation and Language</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj81OhDAUhbtxYUYfwJV9AfAWaAtLQ_xLMLOQPblTbqEJP01Bw_j04ujqnJwvOcnH2J2AOMulhAcMm_uKhRZJDKkoimvWlD0GNCsF9-2mjq898f7sKUR-30faAV88GuKz5dVH_c4HnLpP7IiPc0vDwu0c-Og2armZp5W2laP3gzO4unlabtiVxWGh2_88sPr5qS5fo-r48lY-VhEqXUTqlKRksAAlLQiVJrI1BNCi1KdCg5HK7gVsnlgNAJiLTFFmrc5bAg2UHtj93-3FsPHBjRjOza9pczFNfwDXa09z</recordid><startdate>20171208</startdate><enddate>20171208</enddate><creator>Akinwande, Victor</creator><creator>Remy, Sekou L</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20171208</creationdate><title>Characterizing the hyper-parameter space of LSTM language models for mixed context applications</title><author>Akinwande, Victor ; Remy, Sekou L</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a679-6b23eca9065f016325dce00da57b970c56f7b90f82f7000a8146e4ff78de070e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Computer Science - Computation and Language</topic><toplevel>online_resources</toplevel><creatorcontrib>Akinwande, Victor</creatorcontrib><creatorcontrib>Remy, Sekou L</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Akinwande, Victor</au><au>Remy, Sekou L</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Characterizing the hyper-parameter space of LSTM language models for mixed context applications</atitle><date>2017-12-08</date><risdate>2017</risdate><abstract>Applying state of the art deep learning models to novel real world datasets gives a practical evaluation of the generalizability of these models. Of importance in this process is how sensitive the hyper parameters of such models are to novel datasets as this would affect the reproducibility of a model. We present work to characterize the hyper parameter space of an LSTM for language modeling on a code-mixed corpus. We observe that the evaluated model shows minimal sensitivity to our novel dataset bar a few hyper parameters.</abstract><doi>10.48550/arxiv.1712.03199</doi><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier	DOI: 10.48550/arxiv.1712.03199
ispartof
issn
language	eng
recordid	cdi_arxiv_primary_1712_03199
source	arXiv.org
subjects	Computer Science - Computation and Language
title	Characterizing the hyper-parameter space of LSTM language models for mixed context applications
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-01T05%3A45%3A05IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Characterizing%20the%20hyper-parameter%20space%20of%20LSTM%20language%20models%20for%20mixed%20context%20applications&rft.au=Akinwande,%20Victor&rft.date=2017-12-08&rft_id=info:doi/10.48550/arxiv.1712.03199&rft_dat=%3Carxiv_GOX%3E1712_03199%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true