Text2App: A Framework for Creating Android Apps from Text Descriptions
We present Text2App -- a framework that allows users to create functional Android applications from natural language specifications. The conventional method of source code generation tries to generate source code directly, which is impractical for creating complex software. We overcome this limitati...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2021-07 |
---|---|
Hauptverfasser: | , , , |
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 | Masum Hasan Kazi, Sajeed Mehrab Wasi Uddin Ahmad Shahriyar, Rifat |
description | We present Text2App -- a framework that allows users to create functional Android applications from natural language specifications. The conventional method of source code generation tries to generate source code directly, which is impractical for creating complex software. We overcome this limitation by transforming natural language into an abstract intermediate formal language representing an application with a substantially smaller number of tokens. The intermediate formal representation is then compiled into target source codes. This abstraction of programming details allows seq2seq networks to learn complex application structures with less overhead. In order to train sequence models, we introduce a data synthesis method grounded in a human survey. We demonstrate that Text2App generalizes well to unseen combination of app components and it is capable of handling noisy natural language instructions. We explore the possibility of creating applications from highly abstract instructions by coupling our system with GPT-3 -- a large pretrained language model. We perform an extensive human evaluation and identify the capabilities and limitations of our system. The source code, a ready-to-run demo notebook, and a demo video are publicly available at \url{https://github.com/text2app/Text2App}. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2515481278</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2515481278</sourcerecordid><originalsourceid>FETCH-proquest_journals_25154812783</originalsourceid><addsrcrecordid>eNqNi9EKgjAUQEcQJOU_XOhZ0DuX0ptY0gf4LpJbzHJbd5P6_Az6gJ7OwzlnxSLkPEvKHHHDYu_HNE3xUKAQPGJNK98BK-eOUEFD_SRflu6gLEFNsg_a3KAyA1k9wFJ5UGQn-E5wkv5K2gVtjd-xteofXsY_btm-Obf1JXFkn7P0oRvtTGZRHYpM5GWGRcn_qz4-Tjp7</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2515481278</pqid></control><display><type>article</type><title>Text2App: A Framework for Creating Android Apps from Text Descriptions</title><source>Free E- Journals</source><creator>Masum Hasan ; Kazi, Sajeed Mehrab ; Wasi Uddin Ahmad ; Shahriyar, Rifat</creator><creatorcontrib>Masum Hasan ; Kazi, Sajeed Mehrab ; Wasi Uddin Ahmad ; Shahriyar, Rifat</creatorcontrib><description>We present Text2App -- a framework that allows users to create functional Android applications from natural language specifications. The conventional method of source code generation tries to generate source code directly, which is impractical for creating complex software. We overcome this limitation by transforming natural language into an abstract intermediate formal language representing an application with a substantially smaller number of tokens. The intermediate formal representation is then compiled into target source codes. This abstraction of programming details allows seq2seq networks to learn complex application structures with less overhead. In order to train sequence models, we introduce a data synthesis method grounded in a human survey. We demonstrate that Text2App generalizes well to unseen combination of app components and it is capable of handling noisy natural language instructions. We explore the possibility of creating applications from highly abstract instructions by coupling our system with GPT-3 -- a large pretrained language model. We perform an extensive human evaluation and identify the capabilities and limitations of our system. The source code, a ready-to-run demo notebook, and a demo video are publicly available at \url{https://github.com/text2app/Text2App}.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Applications programs ; Language ; Materials handling ; Model testing ; Natural language ; Source code</subject><ispartof>arXiv.org, 2021-07</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>776,780</link.rule.ids></links><search><creatorcontrib>Masum Hasan</creatorcontrib><creatorcontrib>Kazi, Sajeed Mehrab</creatorcontrib><creatorcontrib>Wasi Uddin Ahmad</creatorcontrib><creatorcontrib>Shahriyar, Rifat</creatorcontrib><title>Text2App: A Framework for Creating Android Apps from Text Descriptions</title><title>arXiv.org</title><description>We present Text2App -- a framework that allows users to create functional Android applications from natural language specifications. The conventional method of source code generation tries to generate source code directly, which is impractical for creating complex software. We overcome this limitation by transforming natural language into an abstract intermediate formal language representing an application with a substantially smaller number of tokens. The intermediate formal representation is then compiled into target source codes. This abstraction of programming details allows seq2seq networks to learn complex application structures with less overhead. In order to train sequence models, we introduce a data synthesis method grounded in a human survey. We demonstrate that Text2App generalizes well to unseen combination of app components and it is capable of handling noisy natural language instructions. We explore the possibility of creating applications from highly abstract instructions by coupling our system with GPT-3 -- a large pretrained language model. We perform an extensive human evaluation and identify the capabilities and limitations of our system. The source code, a ready-to-run demo notebook, and a demo video are publicly available at \url{https://github.com/text2app/Text2App}.</description><subject>Applications programs</subject><subject>Language</subject><subject>Materials handling</subject><subject>Model testing</subject><subject>Natural language</subject><subject>Source code</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNqNi9EKgjAUQEcQJOU_XOhZ0DuX0ptY0gf4LpJbzHJbd5P6_Az6gJ7OwzlnxSLkPEvKHHHDYu_HNE3xUKAQPGJNK98BK-eOUEFD_SRflu6gLEFNsg_a3KAyA1k9wFJ5UGQn-E5wkv5K2gVtjd-xteofXsY_btm-Obf1JXFkn7P0oRvtTGZRHYpM5GWGRcn_qz4-Tjp7</recordid><startdate>20210707</startdate><enddate>20210707</enddate><creator>Masum Hasan</creator><creator>Kazi, Sajeed Mehrab</creator><creator>Wasi Uddin Ahmad</creator><creator>Shahriyar, Rifat</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>20210707</creationdate><title>Text2App: A Framework for Creating Android Apps from Text Descriptions</title><author>Masum Hasan ; Kazi, Sajeed Mehrab ; Wasi Uddin Ahmad ; Shahriyar, Rifat</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_25154812783</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Applications programs</topic><topic>Language</topic><topic>Materials handling</topic><topic>Model testing</topic><topic>Natural language</topic><topic>Source code</topic><toplevel>online_resources</toplevel><creatorcontrib>Masum Hasan</creatorcontrib><creatorcontrib>Kazi, Sajeed Mehrab</creatorcontrib><creatorcontrib>Wasi Uddin Ahmad</creatorcontrib><creatorcontrib>Shahriyar, Rifat</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & 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>Masum Hasan</au><au>Kazi, Sajeed Mehrab</au><au>Wasi Uddin Ahmad</au><au>Shahriyar, Rifat</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Text2App: A Framework for Creating Android Apps from Text Descriptions</atitle><jtitle>arXiv.org</jtitle><date>2021-07-07</date><risdate>2021</risdate><eissn>2331-8422</eissn><abstract>We present Text2App -- a framework that allows users to create functional Android applications from natural language specifications. The conventional method of source code generation tries to generate source code directly, which is impractical for creating complex software. We overcome this limitation by transforming natural language into an abstract intermediate formal language representing an application with a substantially smaller number of tokens. The intermediate formal representation is then compiled into target source codes. This abstraction of programming details allows seq2seq networks to learn complex application structures with less overhead. In order to train sequence models, we introduce a data synthesis method grounded in a human survey. We demonstrate that Text2App generalizes well to unseen combination of app components and it is capable of handling noisy natural language instructions. We explore the possibility of creating applications from highly abstract instructions by coupling our system with GPT-3 -- a large pretrained language model. We perform an extensive human evaluation and identify the capabilities and limitations of our system. The source code, a ready-to-run demo notebook, and a demo video are publicly available at \url{https://github.com/text2app/Text2App}.</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, 2021-07 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_2515481278 |
source | Free E- Journals |
subjects | Applications programs Language Materials handling Model testing Natural language Source code |
title | Text2App: A Framework for Creating Android Apps from Text Descriptions |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-27T09%3A13%3A51IST&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=Text2App:%20A%20Framework%20for%20Creating%20Android%20Apps%20from%20Text%20Descriptions&rft.jtitle=arXiv.org&rft.au=Masum%20Hasan&rft.date=2021-07-07&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2515481278%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2515481278&rft_id=info:pmid/&rfr_iscdi=true |