CFO: A Framework for Building Production NLP Systems

CFO: A Framework for Building Production NLP Systems

This paper introduces a novel orchestration framework, called CFO (COMPUTATION FLOW ORCHESTRATOR), for building, experimenting with, and deploying interactive NLP (Natural Language Processing) and IR (Information Retrieval) systems to production environments. We then demonstrate a question answering...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2020-06
Hauptverfasser: Chakravarti, Rishav, Pendus, Cezar, Sakrajda, Andrzej, Ferritto, Anthony, Pan, Lin, Glass, Michael, Castelli, Vittorio, Murdock, J William, Radu Florian, Roukos, Salim, Sil, Avirup
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Computation and Language
Computer Science - Information Retrieval
Information retrieval
Natural language processing
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 Chakravarti, Rishav
Pendus, Cezar
Sakrajda, Andrzej
Ferritto, Anthony
Pan, Lin
Glass, Michael
Castelli, Vittorio
Murdock, J William
Radu Florian
Roukos, Salim
Sil, Avirup
description This paper introduces a novel orchestration framework, called CFO (COMPUTATION FLOW ORCHESTRATOR), for building, experimenting with, and deploying interactive NLP (Natural Language Processing) and IR (Information Retrieval) systems to production environments. We then demonstrate a question answering system built using this framework which incorporates state-of-the-art BERT based MRC (Machine Reading Comprehension) with IR components to enable end-to-end answer retrieval. Results from the demo system are shown to be high quality in both academic and industry domain specific settings. Finally, we discuss best practices when (pre-)training BERT based MRC models for production systems.
doi_str_mv 10.48550/arxiv.1908.06121
format Article
fullrecord <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_1908_06121</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2276715014</sourcerecordid><originalsourceid>FETCH-LOGICAL-a524-79286998ce748f5d856dffed207ca9133c287d441a4d3124107b01c268c5cb4d3</originalsourceid><addsrcrecordid>eNotj11LwzAYhYMgOOZ-gFcGvG5N3nzWu1nsFIYbuPuSJal0rs1MW3X_3rp5deDwcDgPQjeUpFwLQe5N_Km_UpoRnRJJgV6gCTBGE80BrtCs63aEEJAKhGATxPNi9YDnuIim8d8hfuAqRPw41HtXt-94HYMbbF-HFr8u1_jt2PW-6a7RZWX2nZ_95xRtiqdN_pwsV4uXfL5MjACeqAy0zDJtveK6Ek4L6arKOyDKmowyZkErxzk13DEKnBK1JdSC1FbY7dhN0e159qRUHmLdmHgs_9TKk9pI3J2JQwyfg-_6cheG2I6fSgAlFRWEcvYLBBBObA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2276715014</pqid></control><display><type>article</type><title>CFO: A Framework for Building Production NLP Systems</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Chakravarti, Rishav ; Pendus, Cezar ; Sakrajda, Andrzej ; Ferritto, Anthony ; Pan, Lin ; Glass, Michael ; Castelli, Vittorio ; Murdock, J William ; Radu Florian ; Roukos, Salim ; Sil, Avirup</creator><creatorcontrib>Chakravarti, Rishav ; Pendus, Cezar ; Sakrajda, Andrzej ; Ferritto, Anthony ; Pan, Lin ; Glass, Michael ; Castelli, Vittorio ; Murdock, J William ; Radu Florian ; Roukos, Salim ; Sil, Avirup</creatorcontrib><description>This paper introduces a novel orchestration framework, called CFO (COMPUTATION FLOW ORCHESTRATOR), for building, experimenting with, and deploying interactive NLP (Natural Language Processing) and IR (Information Retrieval) systems to production environments. We then demonstrate a question answering system built using this framework which incorporates state-of-the-art BERT based MRC (Machine Reading Comprehension) with IR components to enable end-to-end answer retrieval. Results from the demo system are shown to be high quality in both academic and industry domain specific settings. Finally, we discuss best practices when (pre-)training BERT based MRC models for production systems.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.1908.06121</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Computer Science - Computation and Language ; Computer Science - Information Retrieval ; Information retrieval ; Natural language processing</subject><ispartof>arXiv.org, 2020-06</ispartof><rights>2020. 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><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>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,780,881,27902</link.rule.ids><backlink>$$Uhttps://doi.org/10.48550/arXiv.1908.06121$$DView paper in arXiv$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.18653/v1/D19-3006$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink></links><search><creatorcontrib>Chakravarti, Rishav</creatorcontrib><creatorcontrib>Pendus, Cezar</creatorcontrib><creatorcontrib>Sakrajda, Andrzej</creatorcontrib><creatorcontrib>Ferritto, Anthony</creatorcontrib><creatorcontrib>Pan, Lin</creatorcontrib><creatorcontrib>Glass, Michael</creatorcontrib><creatorcontrib>Castelli, Vittorio</creatorcontrib><creatorcontrib>Murdock, J William</creatorcontrib><creatorcontrib>Radu Florian</creatorcontrib><creatorcontrib>Roukos, Salim</creatorcontrib><creatorcontrib>Sil, Avirup</creatorcontrib><title>CFO: A Framework for Building Production NLP Systems</title><title>arXiv.org</title><description>This paper introduces a novel orchestration framework, called CFO (COMPUTATION FLOW ORCHESTRATOR), for building, experimenting with, and deploying interactive NLP (Natural Language Processing) and IR (Information Retrieval) systems to production environments. We then demonstrate a question answering system built using this framework which incorporates state-of-the-art BERT based MRC (Machine Reading Comprehension) with IR components to enable end-to-end answer retrieval. Results from the demo system are shown to be high quality in both academic and industry domain specific settings. Finally, we discuss best practices when (pre-)training BERT based MRC models for production systems.</description><subject>Computer Science - Computation and Language</subject><subject>Computer Science - Information Retrieval</subject><subject>Information retrieval</subject><subject>Natural language processing</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><sourceid>GOX</sourceid><recordid>eNotj11LwzAYhYMgOOZ-gFcGvG5N3nzWu1nsFIYbuPuSJal0rs1MW3X_3rp5deDwcDgPQjeUpFwLQe5N_Km_UpoRnRJJgV6gCTBGE80BrtCs63aEEJAKhGATxPNi9YDnuIim8d8hfuAqRPw41HtXt-94HYMbbF-HFr8u1_jt2PW-6a7RZWX2nZ_95xRtiqdN_pwsV4uXfL5MjACeqAy0zDJtveK6Ek4L6arKOyDKmowyZkErxzk13DEKnBK1JdSC1FbY7dhN0e159qRUHmLdmHgs_9TKk9pI3J2JQwyfg-_6cheG2I6fSgAlFRWEcvYLBBBObA</recordid><startdate>20200619</startdate><enddate>20200619</enddate><creator>Chakravarti, Rishav</creator><creator>Pendus, Cezar</creator><creator>Sakrajda, Andrzej</creator><creator>Ferritto, Anthony</creator><creator>Pan, Lin</creator><creator>Glass, Michael</creator><creator>Castelli, Vittorio</creator><creator>Murdock, J William</creator><creator>Radu Florian</creator><creator>Roukos, Salim</creator><creator>Sil, Avirup</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><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20200619</creationdate><title>CFO: A Framework for Building Production NLP Systems</title><author>Chakravarti, Rishav ; Pendus, Cezar ; Sakrajda, Andrzej ; Ferritto, Anthony ; Pan, Lin ; Glass, Michael ; Castelli, Vittorio ; Murdock, J William ; Radu Florian ; Roukos, Salim ; Sil, Avirup</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a524-79286998ce748f5d856dffed207ca9133c287d441a4d3124107b01c268c5cb4d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer Science - Computation and Language</topic><topic>Computer Science - Information Retrieval</topic><topic>Information retrieval</topic><topic>Natural language processing</topic><toplevel>online_resources</toplevel><creatorcontrib>Chakravarti, Rishav</creatorcontrib><creatorcontrib>Pendus, Cezar</creatorcontrib><creatorcontrib>Sakrajda, Andrzej</creatorcontrib><creatorcontrib>Ferritto, Anthony</creatorcontrib><creatorcontrib>Pan, Lin</creatorcontrib><creatorcontrib>Glass, Michael</creatorcontrib><creatorcontrib>Castelli, Vittorio</creatorcontrib><creatorcontrib>Murdock, J William</creatorcontrib><creatorcontrib>Radu Florian</creatorcontrib><creatorcontrib>Roukos, Salim</creatorcontrib><creatorcontrib>Sil, Avirup</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 (ProQuest)</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><collection>arXiv Computer Science</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Chakravarti, Rishav</au><au>Pendus, Cezar</au><au>Sakrajda, Andrzej</au><au>Ferritto, Anthony</au><au>Pan, Lin</au><au>Glass, Michael</au><au>Castelli, Vittorio</au><au>Murdock, J William</au><au>Radu Florian</au><au>Roukos, Salim</au><au>Sil, Avirup</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>CFO: A Framework for Building Production NLP Systems</atitle><jtitle>arXiv.org</jtitle><date>2020-06-19</date><risdate>2020</risdate><eissn>2331-8422</eissn><abstract>This paper introduces a novel orchestration framework, called CFO (COMPUTATION FLOW ORCHESTRATOR), for building, experimenting with, and deploying interactive NLP (Natural Language Processing) and IR (Information Retrieval) systems to production environments. We then demonstrate a question answering system built using this framework which incorporates state-of-the-art BERT based MRC (Machine Reading Comprehension) with IR components to enable end-to-end answer retrieval. Results from the demo system are shown to be high quality in both academic and industry domain specific settings. Finally, we discuss best practices when (pre-)training BERT based MRC models for production systems.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.1908.06121</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2020-06
issn 2331-8422
language eng
recordid cdi_arxiv_primary_1908_06121
source arXiv.org; Free E- Journals
subjects Computer Science - Computation and Language
Computer Science - Information Retrieval
Information retrieval
Natural language processing
title CFO: A Framework for Building Production NLP Systems
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-08T03%3A01%3A07IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=CFO:%20A%20Framework%20for%20Building%20Production%20NLP%20Systems&rft.jtitle=arXiv.org&rft.au=Chakravarti,%20Rishav&rft.date=2020-06-19&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.1908.06121&rft_dat=%3Cproquest_arxiv%3E2276715014%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2276715014&rft_id=info:pmid/&rfr_iscdi=true