Synthesizing Context-free Grammars from Recurrent Neural Networks (Extended Version)

We present an algorithm for extracting a subclass of the context free grammars (CFGs) from a trained recurrent neural network (RNN). We develop a new framework, pattern rule sets (PRSs), which describe sequences of deterministic finite automata (DFAs) that approximate a non-regular language. We pres...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2021-03
Hauptverfasser: Yellin, Daniel M, Weiss, Gail
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Yellin, Daniel M
Weiss, Gail
description We present an algorithm for extracting a subclass of the context free grammars (CFGs) from a trained recurrent neural network (RNN). We develop a new framework, pattern rule sets (PRSs), which describe sequences of deterministic finite automata (DFAs) that approximate a non-regular language. We present an algorithm for recovering the PRS behind a sequence of such automata, and apply it to the sequences of automata extracted from trained RNNs using the L* algorithm. We then show how the PRS may converted into a CFG, enabling a familiar and useful presentation of the learned language. Extracting the learned language of an RNN is important to facilitate understanding of the RNN and to verify its correctness. Furthermore, the extracted CFG can augment the RNN in classifying correct sentences, as the RNN's predictive accuracy decreases when the recursion depth and distance between matching delimiters of its input sequences increases.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2479575105</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2479575105</sourcerecordid><originalsourceid>FETCH-proquest_journals_24795751053</originalsourceid><addsrcrecordid>eNqNyrEOgjAUQNHGxESi_EMTFx1ISktFZ4I6OShxJY08FIRWX0tEv14GP8DpDPeOiMeFCIN1xPmE-NbWjDG-irmUwiPZ6a3dDWz1qfSVJkY76F1QIgDdoWpbhZaWaFp6hEuHCNrRA3SomgH3Mni3dJH2DnQBBT0D2sro5YyMS9VY8H9OyXybZsk-eKB5dmBdXpsO9ZByHsUbGcuQSfHf9QW98kDK</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2479575105</pqid></control><display><type>article</type><title>Synthesizing Context-free Grammars from Recurrent Neural Networks (Extended Version)</title><source>Free E- Journals</source><creator>Yellin, Daniel M ; Weiss, Gail</creator><creatorcontrib>Yellin, Daniel M ; Weiss, Gail</creatorcontrib><description>We present an algorithm for extracting a subclass of the context free grammars (CFGs) from a trained recurrent neural network (RNN). We develop a new framework, pattern rule sets (PRSs), which describe sequences of deterministic finite automata (DFAs) that approximate a non-regular language. We present an algorithm for recovering the PRS behind a sequence of such automata, and apply it to the sequences of automata extracted from trained RNNs using the L* algorithm. We then show how the PRS may converted into a CFG, enabling a familiar and useful presentation of the learned language. Extracting the learned language of an RNN is important to facilitate understanding of the RNN and to verify its correctness. Furthermore, the extracted CFG can augment the RNN in classifying correct sentences, as the RNN's predictive accuracy decreases when the recursion depth and distance between matching delimiters of its input sequences increases.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Context ; Grammars ; Neural networks ; Recurrent neural networks ; Sentences</subject><ispartof>arXiv.org, 2021-03</ispartof><rights>2021. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</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>780,784</link.rule.ids></links><search><creatorcontrib>Yellin, Daniel M</creatorcontrib><creatorcontrib>Weiss, Gail</creatorcontrib><title>Synthesizing Context-free Grammars from Recurrent Neural Networks (Extended Version)</title><title>arXiv.org</title><description>We present an algorithm for extracting a subclass of the context free grammars (CFGs) from a trained recurrent neural network (RNN). We develop a new framework, pattern rule sets (PRSs), which describe sequences of deterministic finite automata (DFAs) that approximate a non-regular language. We present an algorithm for recovering the PRS behind a sequence of such automata, and apply it to the sequences of automata extracted from trained RNNs using the L* algorithm. We then show how the PRS may converted into a CFG, enabling a familiar and useful presentation of the learned language. Extracting the learned language of an RNN is important to facilitate understanding of the RNN and to verify its correctness. Furthermore, the extracted CFG can augment the RNN in classifying correct sentences, as the RNN's predictive accuracy decreases when the recursion depth and distance between matching delimiters of its input sequences increases.</description><subject>Algorithms</subject><subject>Context</subject><subject>Grammars</subject><subject>Neural networks</subject><subject>Recurrent neural networks</subject><subject>Sentences</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNyrEOgjAUQNHGxESi_EMTFx1ISktFZ4I6OShxJY08FIRWX0tEv14GP8DpDPeOiMeFCIN1xPmE-NbWjDG-irmUwiPZ6a3dDWz1qfSVJkY76F1QIgDdoWpbhZaWaFp6hEuHCNrRA3SomgH3Mni3dJH2DnQBBT0D2sro5YyMS9VY8H9OyXybZsk-eKB5dmBdXpsO9ZByHsUbGcuQSfHf9QW98kDK</recordid><startdate>20210328</startdate><enddate>20210328</enddate><creator>Yellin, Daniel M</creator><creator>Weiss, Gail</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20210328</creationdate><title>Synthesizing Context-free Grammars from Recurrent Neural Networks (Extended Version)</title><author>Yellin, Daniel M ; Weiss, Gail</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_24795751053</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Algorithms</topic><topic>Context</topic><topic>Grammars</topic><topic>Neural networks</topic><topic>Recurrent neural networks</topic><topic>Sentences</topic><toplevel>online_resources</toplevel><creatorcontrib>Yellin, Daniel M</creatorcontrib><creatorcontrib>Weiss, Gail</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yellin, Daniel M</au><au>Weiss, Gail</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Synthesizing Context-free Grammars from Recurrent Neural Networks (Extended Version)</atitle><jtitle>arXiv.org</jtitle><date>2021-03-28</date><risdate>2021</risdate><eissn>2331-8422</eissn><abstract>We present an algorithm for extracting a subclass of the context free grammars (CFGs) from a trained recurrent neural network (RNN). We develop a new framework, pattern rule sets (PRSs), which describe sequences of deterministic finite automata (DFAs) that approximate a non-regular language. We present an algorithm for recovering the PRS behind a sequence of such automata, and apply it to the sequences of automata extracted from trained RNNs using the L* algorithm. We then show how the PRS may converted into a CFG, enabling a familiar and useful presentation of the learned language. Extracting the learned language of an RNN is important to facilitate understanding of the RNN and to verify its correctness. Furthermore, the extracted CFG can augment the RNN in classifying correct sentences, as the RNN's predictive accuracy decreases when the recursion depth and distance between matching delimiters of its input sequences increases.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2021-03
issn 2331-8422
language eng
recordid cdi_proquest_journals_2479575105
source Free E- Journals
subjects Algorithms
Context
Grammars
Neural networks
Recurrent neural networks
Sentences
title Synthesizing Context-free Grammars from Recurrent Neural Networks (Extended Version)
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-11T18%3A29%3A04IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Synthesizing%20Context-free%20Grammars%20from%20Recurrent%20Neural%20Networks%20(Extended%20Version)&rft.jtitle=arXiv.org&rft.au=Yellin,%20Daniel%20M&rft.date=2021-03-28&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2479575105%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2479575105&rft_id=info:pmid/&rfr_iscdi=true