LEARNING PROGRAM, LEARNING METHOD, AND LEARNING APPARATUS
To provide a learning program, a learning method, and a learning apparatus which realizes learning which prevents a summary with characters exceeding limitation from being overestimated.SOLUTION: A learning apparatus 10, when learning a model on the basis of multiplicity of a word calculated among a...
Saved in:
Main Author | |
---|---|
Format | Patent |
Language | English Japanese |
Published |
31.01.2019
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | To provide a learning program, a learning method, and a learning apparatus which realizes learning which prevents a summary with characters exceeding limitation from being overestimated.SOLUTION: A learning apparatus 10, when learning a model on the basis of multiplicity of a word calculated among a system summary and a reference summary, uses sentences within the limitation in characters of the system summary for calculating multiplicity, and excludes sentences exceeding the limitation in characters of the system summary from an object of multiplicity calculation. Learning of a generation model is carried out by using evaluation in which a reference summary corresponding to an input summary of the sentences within the limitation in characters is correct.SELECTED DRAWING: Figure 1
【課題】制限字数を超える要約が過大評価されない学習を実現する学習プログラム、学習方法及び学習装置を提供する。【解決手段】学習装置10は、システム要約および参照要約の間で算出する単語の重複度に基づいてモデルを学習する際に、システム要約のうち制限字数内の文まで重複度の算出に用い、システム要約のうち制限字数を超える部分が重複度の算出対象から除外する。この制限字数内の文の、入力文に対応する参照要約を正解とした評価、を用いて、生成モデルの学習を行う。【選択図】図1 |
---|---|
AbstractList | To provide a learning program, a learning method, and a learning apparatus which realizes learning which prevents a summary with characters exceeding limitation from being overestimated.SOLUTION: A learning apparatus 10, when learning a model on the basis of multiplicity of a word calculated among a system summary and a reference summary, uses sentences within the limitation in characters of the system summary for calculating multiplicity, and excludes sentences exceeding the limitation in characters of the system summary from an object of multiplicity calculation. Learning of a generation model is carried out by using evaluation in which a reference summary corresponding to an input summary of the sentences within the limitation in characters is correct.SELECTED DRAWING: Figure 1
【課題】制限字数を超える要約が過大評価されない学習を実現する学習プログラム、学習方法及び学習装置を提供する。【解決手段】学習装置10は、システム要約および参照要約の間で算出する単語の重複度に基づいてモデルを学習する際に、システム要約のうち制限字数内の文まで重複度の算出に用い、システム要約のうち制限字数を超える部分が重複度の算出対象から除外する。この制限字数内の文の、入力文に対応する参照要約を正解とした評価、を用いて、生成モデルの学習を行う。【選択図】図1 |
Author | MAKINO TAKUYA |
Author_xml | – fullname: MAKINO TAKUYA |
BookMark | eNrjYmDJy89L5WSw9HF1DPLz9HNXCAjydw9y9NVRgIv4uoZ4-LvoKDj6uSAEHQMCHIMcQ0KDeRhY0xJzilN5oTQ3g5Kba4izh25qQX58anFBYnJqXmpJvFeAkYGhpYGhmZGxpaMxUYoAy9wquQ |
ContentType | Patent |
DBID | EVB |
DatabaseName | esp@cenet |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: EVB name: esp@cenet url: http://worldwide.espacenet.com/singleLineSearch?locale=en_EP sourceTypes: Open Access Repository |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Medicine Chemistry Sciences Physics |
DocumentTitleAlternate | 学習プログラム、学習方法及び学習装置 |
ExternalDocumentID | JP2019016239A |
GroupedDBID | EVB |
ID | FETCH-epo_espacenet_JP2019016239A3 |
IEDL.DBID | EVB |
IngestDate | Fri Jul 19 12:55:22 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English Japanese |
LinkModel | DirectLink |
MergedId | FETCHMERGED-epo_espacenet_JP2019016239A3 |
Notes | Application Number: JP20170134114 |
OpenAccessLink | https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20190131&DB=EPODOC&CC=JP&NR=2019016239A |
ParticipantIDs | epo_espacenet_JP2019016239A |
PublicationCentury | 2000 |
PublicationDate | 20190131 |
PublicationDateYYYYMMDD | 2019-01-31 |
PublicationDate_xml | – month: 01 year: 2019 text: 20190131 day: 31 |
PublicationDecade | 2010 |
PublicationYear | 2019 |
RelatedCompanies | FUJITSU LTD |
RelatedCompanies_xml | – name: FUJITSU LTD |
Score | 3.30928 |
Snippet | To provide a learning program, a learning method, and a learning apparatus which realizes learning which prevents a summary with characters exceeding... |
SourceID | epo |
SourceType | Open Access Repository |
SubjectTerms | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
Title | LEARNING PROGRAM, LEARNING METHOD, AND LEARNING APPARATUS |
URI | https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20190131&DB=EPODOC&locale=&CC=JP&NR=2019016239A |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3dS8MwED_m_HzTqahTKSJ7WnHdsrZ5KJL1Y3XYNtRO9jbarIIK27AV_32vpft42mMucFwS7n53l7sE4JEogigxJTI6q32ZIAbIiaBU_lBVqpOZrglSNAp7vuqOyWjSn9Tge9ULU74T-lc-jogaJVDf89JeLzdJLKusrcyekk8kLZ6dyLBaVXRcoBsaFWtg2DywArNlmsaIt_ywmkOsp2wP9tGP1or6L_t9ULSlLLcxxTmFA47s5vkZ1L7iBhybq6_XGnDkVTfeDTgsSzRFhsRKDbNzoK82C_0XfyjxMBiGzGtLa4pnR25gtSXmWxsi45yFLBq_XcCDY0emK6M00_XapyO-JXnvEurzxTy9AomoXarrqtYVHR1jnFmiiF7cUXSakA6eSnoNzR2MbnbONuGkGBWJhp5yC_X85ze9Q-jNk_tyy_4BxiSAKQ |
link.rule.ids | 230,309,783,888,25578,76884 |
linkProvider | European Patent Office |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3dT8JADG8QP_BNUaPix2IMTywyOMbdAzHHNhjItsschDeyHZioCRCZ8d-3W8bHE69t0vTu0v7a3rUH8Ew0SbSQERWD1YZKEAPUSDKmfug6o2RKm5IkjcKOq9tD0h83xjn4XvfCpHNC_9LhiGhREu09Tv31clvEMtO3lauX6BNJi9dO0DLLWXacoBs6FbPdsoRnekbZMFp9UXb9jIdYz_gBHGKMTZNB-9aonbSlLHcxpXMGRwLFzeNzyH2FRSgY66_XinDiZDfeRThOn2jKFRIzM1xdABtY3Hd7blcRvtf1uVNRNhTHCmzPrCjcNbdELgT3eTB8v4SnjhUYtoraTDZrn_TFjub1K8jPF_PZNShErzFK9WZNVinmONNIk_WwqlEWkSqeyuwGSnsE3e7lPkLBDpzBZNBz30pwmnCSokNdu4N8_PM7u0cYjqOHdPv-AfDmgxk |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Apatent&rft.title=LEARNING+PROGRAM%2C+LEARNING+METHOD%2C+AND+LEARNING+APPARATUS&rft.inventor=MAKINO+TAKUYA&rft.date=2019-01-31&rft.externalDBID=A&rft.externalDocID=JP2019016239A |