Statistically driven sentence realizing method and apparatus

Statistically driven sentence realizing method and apparatus

A method of, and system for, generating a sentence from a semantic representation maps the semantic representation to an unordered set of syntactic nodes. Simplified generation grammar rules and statistical goodness measure values from a corresponding analysis grammar are then used to create a tree...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: CALCAGNO MICHAEL V, HUMPHREYS KEVIN W, WEISE DAVID NEAL
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 CALCAGNO MICHAEL V
HUMPHREYS KEVIN W
WEISE DAVID NEAL
description A method of, and system for, generating a sentence from a semantic representation maps the semantic representation to an unordered set of syntactic nodes. Simplified generation grammar rules and statistical goodness measure values from a corresponding analysis grammar are then used to create a tree structure to order the syntactic nodes. The sentence is then generated from the tree structure. The generation grammar is a simplified (context free) version of a corresponding full (context sensitive) analysis grammar. In the generation grammar, conditions on each rule are ignored except those directly related to the semantic representation. The statistical goodness measure values, which are calculated through an analysis training phase in which a corpus of example sentences is processed using the full analysis grammar, are used to guide the generation choice to prefer substructures most commonly found in a particular syntactic/semantic context during analysis.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US7003445B2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US7003445B2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US7003445B23</originalsourceid><addsrcrecordid>eNrjZLAJLkksySwuyUxOzMmpVEgpyixLzVMoTs0rSc1LTlUoSk3MyazKzEtXyE0tychPUUjMA-KCgsSixJLSYh4G1rTEnOJUXijNzaDg5hri7KGbWpAfn1pckJicmpdaEh8abG5gYGxiYupkZEyEEgDjCzA0</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Statistically driven sentence realizing method and apparatus</title><source>esp@cenet</source><creator>CALCAGNO MICHAEL V ; HUMPHREYS KEVIN W ; WEISE DAVID NEAL</creator><creatorcontrib>CALCAGNO MICHAEL V ; HUMPHREYS KEVIN W ; WEISE DAVID NEAL</creatorcontrib><description>A method of, and system for, generating a sentence from a semantic representation maps the semantic representation to an unordered set of syntactic nodes. Simplified generation grammar rules and statistical goodness measure values from a corresponding analysis grammar are then used to create a tree structure to order the syntactic nodes. The sentence is then generated from the tree structure. The generation grammar is a simplified (context free) version of a corresponding full (context sensitive) analysis grammar. In the generation grammar, conditions on each rule are ignored except those directly related to the semantic representation. The statistical goodness measure values, which are calculated through an analysis training phase in which a corpus of example sentences is processed using the full analysis grammar, are used to guide the generation choice to prefer substructures most commonly found in a particular syntactic/semantic context during analysis.</description><language>eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2006</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=20060221&amp;DB=EPODOC&amp;CC=US&amp;NR=7003445B2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25555,76308</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20060221&amp;DB=EPODOC&amp;CC=US&amp;NR=7003445B2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>CALCAGNO MICHAEL V</creatorcontrib><creatorcontrib>HUMPHREYS KEVIN W</creatorcontrib><creatorcontrib>WEISE DAVID NEAL</creatorcontrib><title>Statistically driven sentence realizing method and apparatus</title><description>A method of, and system for, generating a sentence from a semantic representation maps the semantic representation to an unordered set of syntactic nodes. Simplified generation grammar rules and statistical goodness measure values from a corresponding analysis grammar are then used to create a tree structure to order the syntactic nodes. The sentence is then generated from the tree structure. The generation grammar is a simplified (context free) version of a corresponding full (context sensitive) analysis grammar. In the generation grammar, conditions on each rule are ignored except those directly related to the semantic representation. The statistical goodness measure values, which are calculated through an analysis training phase in which a corpus of example sentences is processed using the full analysis grammar, are used to guide the generation choice to prefer substructures most commonly found in a particular syntactic/semantic context during analysis.</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>2006</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLAJLkksySwuyUxOzMmpVEgpyixLzVMoTs0rSc1LTlUoSk3MyazKzEtXyE0tychPUUjMA-KCgsSixJLSYh4G1rTEnOJUXijNzaDg5hri7KGbWpAfn1pckJicmpdaEh8abG5gYGxiYupkZEyEEgDjCzA0</recordid><startdate>20060221</startdate><enddate>20060221</enddate><creator>CALCAGNO MICHAEL V</creator><creator>HUMPHREYS KEVIN W</creator><creator>WEISE DAVID NEAL</creator><scope>EVB</scope></search><sort><creationdate>20060221</creationdate><title>Statistically driven sentence realizing method and apparatus</title><author>CALCAGNO MICHAEL V ; HUMPHREYS KEVIN W ; WEISE DAVID NEAL</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US7003445B23</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2006</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>CALCAGNO MICHAEL V</creatorcontrib><creatorcontrib>HUMPHREYS KEVIN W</creatorcontrib><creatorcontrib>WEISE DAVID NEAL</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>CALCAGNO MICHAEL V</au><au>HUMPHREYS KEVIN W</au><au>WEISE DAVID NEAL</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Statistically driven sentence realizing method and apparatus</title><date>2006-02-21</date><risdate>2006</risdate><abstract>A method of, and system for, generating a sentence from a semantic representation maps the semantic representation to an unordered set of syntactic nodes. Simplified generation grammar rules and statistical goodness measure values from a corresponding analysis grammar are then used to create a tree structure to order the syntactic nodes. The sentence is then generated from the tree structure. The generation grammar is a simplified (context free) version of a corresponding full (context sensitive) analysis grammar. In the generation grammar, conditions on each rule are ignored except those directly related to the semantic representation. The statistical goodness measure values, which are calculated through an analysis training phase in which a corpus of example sentences is processed using the full analysis grammar, are used to guide the generation choice to prefer substructures most commonly found in a particular syntactic/semantic context during analysis.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US7003445B2
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title Statistically driven sentence realizing method and apparatus
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T20%3A19%3A48IST&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=CALCAGNO%20MICHAEL%20V&rft.date=2006-02-21&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS7003445B2%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