METHOD AND APPARATUS FOR SELECTING AMONG COMPETING MODELS IN A TOOL FOR BUILDING NATURAL LANGUAGE UNDERSTANDING MODELS

METHOD AND APPARATUS FOR SELECTING AMONG COMPETING MODELS IN A TOOL FOR BUILDING NATURAL LANGUAGE UNDERSTANDING MODELS

Selecting a grammar for use in a machine question-answering system, such as a Natural Language Understanding System, can be difficult for non-experts in such grammars. A tool, according to an example embodiment, can compare annotations of sample sentences, performed correctly by a human, the annotat...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: MARCUS JEFFREY N
Format: Patent
Sprache:eng
Schlagworte:
CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
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 MARCUS JEFFREY N
description Selecting a grammar for use in a machine question-answering system, such as a Natural Language Understanding System, can be difficult for non-experts in such grammars. A tool, according to an example embodiment, can compare annotations of sample sentences, performed correctly by a human, the annotations having intents and mentions, against annotations performed by multiple grammars. Each grammar can be scored, and the system can select the best scored grammar for the user. In one embodiment, a method of selecting a grammar includes comparing manually-generated annotations against machine-generated annotations as a function of a given grammar among multiple grammars. The method can further include applying scores to the machine-generated annotations that are a function of weightings of the intents and mentions. The method can additionally include recommending whether to employ the given grammar based on the scores.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2015032442A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2015032442A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2015032442A13</originalsourceid><addsrcrecordid>eNqNTUkKwkAQzMWDqH9o8Cxk8wGdTGeBmekwyzkEGU-igYjvdwyCVw9dRVFLb5OXItexANTxhgENOm-hYQOWJNWu1y2g4og1q4FWrViQtNBrQHDMco1Xvpfi4-q4YFCCRN16bAm8FmSsix9-5X2yuU63JRy-vEuODbm6O4X5MYZlni7hHp6jt3mandMiL8scs-K_1BvnADol</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>METHOD AND APPARATUS FOR SELECTING AMONG COMPETING MODELS IN A TOOL FOR BUILDING NATURAL LANGUAGE UNDERSTANDING MODELS</title><source>esp@cenet</source><creator>MARCUS JEFFREY N</creator><creatorcontrib>MARCUS JEFFREY N</creatorcontrib><description>Selecting a grammar for use in a machine question-answering system, such as a Natural Language Understanding System, can be difficult for non-experts in such grammars. A tool, according to an example embodiment, can compare annotations of sample sentences, performed correctly by a human, the annotations having intents and mentions, against annotations performed by multiple grammars. Each grammar can be scored, and the system can select the best scored grammar for the user. In one embodiment, a method of selecting a grammar includes comparing manually-generated annotations against machine-generated annotations as a function of a given grammar among multiple grammars. The method can further include applying scores to the machine-generated annotations that are a function of weightings of the intents and mentions. The method can additionally include recommending whether to employ the given grammar based on the scores.</description><language>eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2015</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20150129&amp;DB=EPODOC&amp;CC=US&amp;NR=2015032442A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20150129&amp;DB=EPODOC&amp;CC=US&amp;NR=2015032442A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>MARCUS JEFFREY N</creatorcontrib><title>METHOD AND APPARATUS FOR SELECTING AMONG COMPETING MODELS IN A TOOL FOR BUILDING NATURAL LANGUAGE UNDERSTANDING MODELS</title><description>Selecting a grammar for use in a machine question-answering system, such as a Natural Language Understanding System, can be difficult for non-experts in such grammars. A tool, according to an example embodiment, can compare annotations of sample sentences, performed correctly by a human, the annotations having intents and mentions, against annotations performed by multiple grammars. Each grammar can be scored, and the system can select the best scored grammar for the user. In one embodiment, a method of selecting a grammar includes comparing manually-generated annotations against machine-generated annotations as a function of a given grammar among multiple grammars. The method can further include applying scores to the machine-generated annotations that are a function of weightings of the intents and mentions. The method can additionally include recommending whether to employ the given grammar based on the scores.</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2015</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNTUkKwkAQzMWDqH9o8Cxk8wGdTGeBmekwyzkEGU-igYjvdwyCVw9dRVFLb5OXItexANTxhgENOm-hYQOWJNWu1y2g4og1q4FWrViQtNBrQHDMco1Xvpfi4-q4YFCCRN16bAm8FmSsix9-5X2yuU63JRy-vEuODbm6O4X5MYZlni7hHp6jt3mandMiL8scs-K_1BvnADol</recordid><startdate>20150129</startdate><enddate>20150129</enddate><creator>MARCUS JEFFREY N</creator><scope>EVB</scope></search><sort><creationdate>20150129</creationdate><title>METHOD AND APPARATUS FOR SELECTING AMONG COMPETING MODELS IN A TOOL FOR BUILDING NATURAL LANGUAGE UNDERSTANDING MODELS</title><author>MARCUS JEFFREY N</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2015032442A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2015</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>MARCUS JEFFREY N</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>MARCUS JEFFREY N</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>METHOD AND APPARATUS FOR SELECTING AMONG COMPETING MODELS IN A TOOL FOR BUILDING NATURAL LANGUAGE UNDERSTANDING MODELS</title><date>2015-01-29</date><risdate>2015</risdate><abstract>Selecting a grammar for use in a machine question-answering system, such as a Natural Language Understanding System, can be difficult for non-experts in such grammars. A tool, according to an example embodiment, can compare annotations of sample sentences, performed correctly by a human, the annotations having intents and mentions, against annotations performed by multiple grammars. Each grammar can be scored, and the system can select the best scored grammar for the user. In one embodiment, a method of selecting a grammar includes comparing manually-generated annotations against machine-generated annotations as a function of a given grammar among multiple grammars. The method can further include applying scores to the machine-generated annotations that are a function of weightings of the intents and mentions. The method can additionally include recommending whether to employ the given grammar based on the scores.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US2015032442A1
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title METHOD AND APPARATUS FOR SELECTING AMONG COMPETING MODELS IN A TOOL FOR BUILDING NATURAL LANGUAGE UNDERSTANDING MODELS
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-05T04%3A40%3A51IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=MARCUS%20JEFFREY%20N&rft.date=2015-01-29&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2015032442A1%3C/epo_EVB%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