METHOD AND APPARATUS FOR PROCESSING LANGUAGE BASED ON TRAINED NETWORK MODEL

The present disclosure relates to an artificial intelligence (AI) system utilizing a machine learning algorithm such as deep learning or the like and to the application thereof. According to one embodiment of the present disclosure, a language processing method based on a learning network model comp...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: ANALLE JAMAL ABUAMMAR, BASHAR BASSAM TALAA, RUBA WALEED JAIKAT, ZATER MUHY EDDIN
Format: Patent
Sprache:eng ; kor
Schlagworte:
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 ANALLE JAMAL ABUAMMAR
BASHAR BASSAM TALAA
RUBA WALEED JAIKAT
ZATER MUHY EDDIN
description The present disclosure relates to an artificial intelligence (AI) system utilizing a machine learning algorithm such as deep learning or the like and to the application thereof. According to one embodiment of the present disclosure, a language processing method based on a learning network model comprises the steps of: obtaining a source sentence composed of a plurality of words; obtaining a context vector representing the plurality of words constituting the source sentence; using a learning network model, and determining a plurality of paraphrased sentences composed of paraphrased words for each of the plurality of words constituting the source sentence based on the context vector and similarities between each of the plurality of paraphrased words and the source sentences; and obtaining a preset number of paraphrased sentences from the plurality of paraphrased sentences based on the similarities. 본 개시는 딥러닝 등의 기계 학습 알고리즘을 활용하는 인공지능(AI) 시스템 및 그 응용에 관련된 것이다. 본 개시의 일 실시예에 따른 학습 네트워크 모델 기반의 언어 처리 방법은, 복수의 단어로 구성된 소스 문장(source sentence)을 획득하는 단계; 상기 소스 문장을 구성하는 복수의 단어를 나타내는 컨텍스트 벡터(context vector)를 획득하는 단계; 학습 네트워크 모델을 이용하여, 상기 컨텍스트 벡터를 기초로 상기 소스 문장을 구성하는 복수의 단어 각각에 대한 유의어(paraphrased word)로 구성된 복수의 의역 문장(paraphrased sentence) 및 상기 복수의 의역 문장 각각과 상기 소스 문장 간의 유사도를 결정하는 단계; 및 상기 유사도를 기초로 복수의 의역 문장 중 기 설정된 개수의 의역 문장을 획득하는 단계를 포함한다.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_KR20200135607A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>KR20200135607A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_KR20200135607A3</originalsourceid><addsrcrecordid>eNrjZPD2dQ3x8HdRcPQD4oAAxyDHkNBgBTf_IIWAIH9n1-BgTz93BR9HP_dQR3dXBSfHYFcXBX8_hZAgR08_INPPNSTcP8hbwdffxdWHh4E1LTGnOJUXSnMzKLu5hjh76KYW5MenFhckJqfmpZbEewcZGRgZGBgam5oZmDsaE6cKAClNLk0</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>METHOD AND APPARATUS FOR PROCESSING LANGUAGE BASED ON TRAINED NETWORK MODEL</title><source>esp@cenet</source><creator>ANALLE JAMAL ABUAMMAR ; BASHAR BASSAM TALAA ; RUBA WALEED JAIKAT ; ZATER MUHY EDDIN</creator><creatorcontrib>ANALLE JAMAL ABUAMMAR ; BASHAR BASSAM TALAA ; RUBA WALEED JAIKAT ; ZATER MUHY EDDIN</creatorcontrib><description>The present disclosure relates to an artificial intelligence (AI) system utilizing a machine learning algorithm such as deep learning or the like and to the application thereof. According to one embodiment of the present disclosure, a language processing method based on a learning network model comprises the steps of: obtaining a source sentence composed of a plurality of words; obtaining a context vector representing the plurality of words constituting the source sentence; using a learning network model, and determining a plurality of paraphrased sentences composed of paraphrased words for each of the plurality of words constituting the source sentence based on the context vector and similarities between each of the plurality of paraphrased words and the source sentences; and obtaining a preset number of paraphrased sentences from the plurality of paraphrased sentences based on the similarities. 본 개시는 딥러닝 등의 기계 학습 알고리즘을 활용하는 인공지능(AI) 시스템 및 그 응용에 관련된 것이다. 본 개시의 일 실시예에 따른 학습 네트워크 모델 기반의 언어 처리 방법은, 복수의 단어로 구성된 소스 문장(source sentence)을 획득하는 단계; 상기 소스 문장을 구성하는 복수의 단어를 나타내는 컨텍스트 벡터(context vector)를 획득하는 단계; 학습 네트워크 모델을 이용하여, 상기 컨텍스트 벡터를 기초로 상기 소스 문장을 구성하는 복수의 단어 각각에 대한 유의어(paraphrased word)로 구성된 복수의 의역 문장(paraphrased sentence) 및 상기 복수의 의역 문장 각각과 상기 소스 문장 간의 유사도를 결정하는 단계; 및 상기 유사도를 기초로 복수의 의역 문장 중 기 설정된 개수의 의역 문장을 획득하는 단계를 포함한다.</description><language>eng ; kor</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2020</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=20201203&amp;DB=EPODOC&amp;CC=KR&amp;NR=20200135607A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20201203&amp;DB=EPODOC&amp;CC=KR&amp;NR=20200135607A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ANALLE JAMAL ABUAMMAR</creatorcontrib><creatorcontrib>BASHAR BASSAM TALAA</creatorcontrib><creatorcontrib>RUBA WALEED JAIKAT</creatorcontrib><creatorcontrib>ZATER MUHY EDDIN</creatorcontrib><title>METHOD AND APPARATUS FOR PROCESSING LANGUAGE BASED ON TRAINED NETWORK MODEL</title><description>The present disclosure relates to an artificial intelligence (AI) system utilizing a machine learning algorithm such as deep learning or the like and to the application thereof. According to one embodiment of the present disclosure, a language processing method based on a learning network model comprises the steps of: obtaining a source sentence composed of a plurality of words; obtaining a context vector representing the plurality of words constituting the source sentence; using a learning network model, and determining a plurality of paraphrased sentences composed of paraphrased words for each of the plurality of words constituting the source sentence based on the context vector and similarities between each of the plurality of paraphrased words and the source sentences; and obtaining a preset number of paraphrased sentences from the plurality of paraphrased sentences based on the similarities. 본 개시는 딥러닝 등의 기계 학습 알고리즘을 활용하는 인공지능(AI) 시스템 및 그 응용에 관련된 것이다. 본 개시의 일 실시예에 따른 학습 네트워크 모델 기반의 언어 처리 방법은, 복수의 단어로 구성된 소스 문장(source sentence)을 획득하는 단계; 상기 소스 문장을 구성하는 복수의 단어를 나타내는 컨텍스트 벡터(context vector)를 획득하는 단계; 학습 네트워크 모델을 이용하여, 상기 컨텍스트 벡터를 기초로 상기 소스 문장을 구성하는 복수의 단어 각각에 대한 유의어(paraphrased word)로 구성된 복수의 의역 문장(paraphrased sentence) 및 상기 복수의 의역 문장 각각과 상기 소스 문장 간의 유사도를 결정하는 단계; 및 상기 유사도를 기초로 복수의 의역 문장 중 기 설정된 개수의 의역 문장을 획득하는 단계를 포함한다.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2020</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZPD2dQ3x8HdRcPQD4oAAxyDHkNBgBTf_IIWAIH9n1-BgTz93BR9HP_dQR3dXBSfHYFcXBX8_hZAgR08_INPPNSTcP8hbwdffxdWHh4E1LTGnOJUXSnMzKLu5hjh76KYW5MenFhckJqfmpZbEewcZGRgZGBgam5oZmDsaE6cKAClNLk0</recordid><startdate>20201203</startdate><enddate>20201203</enddate><creator>ANALLE JAMAL ABUAMMAR</creator><creator>BASHAR BASSAM TALAA</creator><creator>RUBA WALEED JAIKAT</creator><creator>ZATER MUHY EDDIN</creator><scope>EVB</scope></search><sort><creationdate>20201203</creationdate><title>METHOD AND APPARATUS FOR PROCESSING LANGUAGE BASED ON TRAINED NETWORK MODEL</title><author>ANALLE JAMAL ABUAMMAR ; BASHAR BASSAM TALAA ; RUBA WALEED JAIKAT ; ZATER MUHY EDDIN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_KR20200135607A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; kor</language><creationdate>2020</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>ANALLE JAMAL ABUAMMAR</creatorcontrib><creatorcontrib>BASHAR BASSAM TALAA</creatorcontrib><creatorcontrib>RUBA WALEED JAIKAT</creatorcontrib><creatorcontrib>ZATER MUHY EDDIN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ANALLE JAMAL ABUAMMAR</au><au>BASHAR BASSAM TALAA</au><au>RUBA WALEED JAIKAT</au><au>ZATER MUHY EDDIN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>METHOD AND APPARATUS FOR PROCESSING LANGUAGE BASED ON TRAINED NETWORK MODEL</title><date>2020-12-03</date><risdate>2020</risdate><abstract>The present disclosure relates to an artificial intelligence (AI) system utilizing a machine learning algorithm such as deep learning or the like and to the application thereof. According to one embodiment of the present disclosure, a language processing method based on a learning network model comprises the steps of: obtaining a source sentence composed of a plurality of words; obtaining a context vector representing the plurality of words constituting the source sentence; using a learning network model, and determining a plurality of paraphrased sentences composed of paraphrased words for each of the plurality of words constituting the source sentence based on the context vector and similarities between each of the plurality of paraphrased words and the source sentences; and obtaining a preset number of paraphrased sentences from the plurality of paraphrased sentences based on the similarities. 본 개시는 딥러닝 등의 기계 학습 알고리즘을 활용하는 인공지능(AI) 시스템 및 그 응용에 관련된 것이다. 본 개시의 일 실시예에 따른 학습 네트워크 모델 기반의 언어 처리 방법은, 복수의 단어로 구성된 소스 문장(source sentence)을 획득하는 단계; 상기 소스 문장을 구성하는 복수의 단어를 나타내는 컨텍스트 벡터(context vector)를 획득하는 단계; 학습 네트워크 모델을 이용하여, 상기 컨텍스트 벡터를 기초로 상기 소스 문장을 구성하는 복수의 단어 각각에 대한 유의어(paraphrased word)로 구성된 복수의 의역 문장(paraphrased sentence) 및 상기 복수의 의역 문장 각각과 상기 소스 문장 간의 유사도를 결정하는 단계; 및 상기 유사도를 기초로 복수의 의역 문장 중 기 설정된 개수의 의역 문장을 획득하는 단계를 포함한다.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng ; kor
recordid cdi_epo_espacenet_KR20200135607A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title METHOD AND APPARATUS FOR PROCESSING LANGUAGE BASED ON TRAINED NETWORK MODEL
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T20%3A57%3A33IST&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=ANALLE%20JAMAL%20ABUAMMAR&rft.date=2020-12-03&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EKR20200135607A%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