{"@context":{"@vocab":"https://cir.nii.ac.jp/schema/1.0/","rdfs":"http://www.w3.org/2000/01/rdf-schema#","dc":"http://purl.org/dc/elements/1.1/","dcterms":"http://purl.org/dc/terms/","foaf":"http://xmlns.com/foaf/0.1/","prism":"http://prismstandard.org/namespaces/basic/2.0/","cinii":"http://ci.nii.ac.jp/ns/1.0/","datacite":"https://schema.datacite.org/meta/kernel-4/","ndl":"http://ndl.go.jp/dcndl/terms/","jpcoar":"https://github.com/JPCOAR/schema/blob/master/2.0/"},"@id":"https://cir.nii.ac.jp/crid/1390571868614366208.json","@type":"Article","productIdentifier":[{"identifier":{"@type":"DOI","@value":"10.5715/jnlp.28.1270"}},{"identifier":{"@type":"URI","@value":"https://www.jstage.jst.go.jp/article/jnlp/28/4/28_1270/_pdf"}},{"identifier":{"@type":"NAID","@value":"130008129477"}}],"dc:title":[{"@language":"en","@value":"A Selection Support System for Enterprise Resource Planning Package Components using Ensembles of Multiple Models with Round-trip Translation"}],"dc:language":"en","description":[{"type":"abstract","notation":[{"@language":"en","@value":"<p>An enterprise resource planning (ERP) package consists of software to support day-to-day business activities and contains multiple components. System engineers combine the most appropriate software components for system integration using ERP packages. Because component selection is a very difficult task, even for experienced system engineers, there is a demand for machine-learning-based systems that support appropriate component selection by reading the text of requirement specifications and predicting suitable components. However, sufficient prediction accuracy has not been achieved thus far as a result of the sparsity and diversity of training data, which consist of specification texts paired with their corresponding components. We implemented round-trip translation at both training and testing times to alleviate the sparsity and diversity problems, adopted pre-trained models to exploit the similarity of text data, and utilized an ensemble of diverse models to take advantage of models for both the original and round-trip translated data. Through experiments with actual project data from ERP system integration, we confirmed that round-trip translation alleviates the problems mentioned above and improves prediction accuracy. As a result, our method achieved sufficient accuracy for practical use. </p>"}],"abstractLicenseFlag":"disallow"}],"creator":[{"@id":"https://cir.nii.ac.jp/crid/1410571868614366209","@type":"Researcher","personIdentifier":[{"@type":"NRID","@value":"9000414743819"}],"foaf:name":[{"@language":"en","@value":"Ideuchi Masao"}],"jpcoar:affiliationName":[{"@language":"en","@value":"FUJITSU LIMITED"},{"@language":"en","@value":"National Institute of Information and Communications Technology"},{"@language":"en","@value":"Nara Institute of Science and Technology"}]},{"@id":"https://cir.nii.ac.jp/crid/1410571868614366215","@type":"Researcher","personIdentifier":[{"@type":"NRID","@value":"9000414743820"}],"foaf:name":[{"@language":"en","@value":"Sakamoto Yohei"}],"jpcoar:affiliationName":[{"@language":"en","@value":"Ridgelinez Limited"}]},{"@id":"https://cir.nii.ac.jp/crid/1410571868614366211","@type":"Researcher","personIdentifier":[{"@type":"NRID","@value":"9000414743821"}],"foaf:name":[{"@language":"en","@value":"Oida Yoshiaki"}],"jpcoar:affiliationName":[{"@language":"en","@value":"FUJITSU LIMITED"},{"@language":"en","@value":"The University of Tokyo"}]},{"@id":"https://cir.nii.ac.jp/crid/1410571868614366210","@type":"Researcher","personIdentifier":[{"@type":"NRID","@value":"9000414743822"}],"foaf:name":[{"@language":"en","@value":"Okada Isaac"}],"jpcoar:affiliationName":[{"@language":"en","@value":"FUJITSU LIMITED"},{"@language":"en","@value":"The University of Tokyo"},{"@language":"en","@value":"Senshu University"}]},{"@id":"https://cir.nii.ac.jp/crid/1410571868614366212","@type":"Researcher","personIdentifier":[{"@type":"NRID","@value":"9000414743823"}],"foaf:name":[{"@language":"en","@value":"Higashiyama Shohei"}],"jpcoar:affiliationName":[{"@language":"en","@value":"National Institute of Information and Communications Technology"},{"@language":"en","@value":"Nara Institute of Science and Technology"}]},{"@id":"https://cir.nii.ac.jp/crid/1410571868614366208","@type":"Researcher","personIdentifier":[{"@type":"NRID","@value":"9000414743824"}],"foaf:name":[{"@language":"en","@value":"Utiyama Masao"}],"jpcoar:affiliationName":[{"@language":"en","@value":"National Institute of Information and Communications Technology"}]},{"@id":"https://cir.nii.ac.jp/crid/1410571868614366213","@type":"Researcher","personIdentifier":[{"@type":"NRID","@value":"9000414743825"}],"foaf:name":[{"@language":"en","@value":"Sumita Eiichiro"}],"jpcoar:affiliationName":[{"@language":"en","@value":"National Institute of Information and Communications Technology"}]},{"@id":"https://cir.nii.ac.jp/crid/1410571868614366214","@type":"Researcher","personIdentifier":[{"@type":"NRID","@value":"9000414743826"}],"foaf:name":[{"@language":"en","@value":"Watanabe Taro"}],"jpcoar:affiliationName":[{"@language":"en","@value":"Nara Institute of Science and Technology"}]}],"publication":{"publicationIdentifier":[{"@type":"PISSN","@value":"13407619"},{"@type":"LISSN","@value":"13407619"},{"@type":"EISSN","@value":"21858314"}],"prism:publicationName":[{"@language":"en","@value":"Journal of Natural Language Processing"},{"@language":"ja","@value":"自然言語処理"},{"@language":"en","@value":"Journal of Natural Language Processing"},{"@language":"ja","@value":"自然言語処理"}],"dc:publisher":[{"@language":"en","@value":"The Association for Natural Language Processing"},{"@language":"ja","@value":"一般社団法人　言語処理学会"}],"prism:publicationDate":"2021","prism:volume":"28","prism:number":"4","prism:startingPage":"1270","prism:endingPage":"1298"},"reviewed":"false","dcterms:accessRights":"http://purl.org/coar/access_right/c_abf2","url":[{"@id":"https://www.jstage.jst.go.jp/article/jnlp/28/4/28_1270/_pdf"}],"availableAt":"2021","foaf:topic":[{"@id":"https://cir.nii.ac.jp/all?q=Round-trip%20Translation","dc:title":"Round-trip Translation"},{"@id":"https://cir.nii.ac.jp/all?q=Data%20Augmentation","dc:title":"Data Augmentation"},{"@id":"https://cir.nii.ac.jp/all?q=Text%20Classification","dc:title":"Text Classification"},{"@id":"https://cir.nii.ac.jp/all?q=Business%20Data","dc:title":"Business Data"}],"relatedProduct":[{"@id":"https://cir.nii.ac.jp/crid/1360011143498276608","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Web service API recommendation for automated mashup creation using multi-objective evolutionary search"}]},{"@id":"https://cir.nii.ac.jp/crid/1360011144243568512","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Stacked regressions"}]},{"@id":"https://cir.nii.ac.jp/crid/1360285707193049088","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Search-based software library recommendation using multi-objective optimization"}]},{"@id":"https://cir.nii.ac.jp/crid/1360845538913474944","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations"}]},{"@id":"https://cir.nii.ac.jp/crid/1360845538961414656","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks"}]},{"@id":"https://cir.nii.ac.jp/crid/1361137045418013312","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"SimilarTech: automatically recommend analogical libraries across different programming languages"}]},{"@id":"https://cir.nii.ac.jp/crid/1361137045842687360","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Ensemble learning: A survey"}]},{"@id":"https://cir.nii.ac.jp/crid/1361137046382402944","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Stacked generalization"}]},{"@id":"https://cir.nii.ac.jp/crid/1361699994896471424","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"fairseq: A Fast, Extensible Toolkit for Sequence Modeling"}]},{"@id":"https://cir.nii.ac.jp/crid/1361699994942548352","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"ParaNMT-50M: Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translations"}]},{"@id":"https://cir.nii.ac.jp/crid/1361699996170093824","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Learning Paraphrastic Sentence Embeddings from Back-Translated Bitext"}]},{"@id":"https://cir.nii.ac.jp/crid/1361981470004221824","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"The NN-Stacking: Feature weighted linear stacking through neural networks"}]},{"@id":"https://cir.nii.ac.jp/crid/1362544418727745664","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Training Products of Experts by Minimizing Contrastive Divergence"}]},{"@id":"https://cir.nii.ac.jp/crid/1362544421143845760","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Enhancing Text Categorization with Semantic-enriched Representation and Training Data Augmentation"}]},{"@id":"https://cir.nii.ac.jp/crid/1362825893654647808","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"PARABANK: Monolingual Bitext Generation and Sentential Paraphrasing via Lexically-Constrained Neural Machine Translation"}]},{"@id":"https://cir.nii.ac.jp/crid/1362825893788826368","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Assessment of conversation co-mentions as a resource for software module recommendation"}]},{"@id":"https://cir.nii.ac.jp/crid/1363107370810406400","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"A Survey of Text Data Augmentation"}]},{"@id":"https://cir.nii.ac.jp/crid/1363388843844061184","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"The Future Digital Work Force:  Robotic Process Automation (RPA)"}]},{"@id":"https://cir.nii.ac.jp/crid/1363388844170699520","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"WordNet"}]},{"@id":"https://cir.nii.ac.jp/crid/1363388844832434816","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing"}]},{"@id":"https://cir.nii.ac.jp/crid/1363388845062521216","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Naver Labs Europe’s Systems for the WMT19 Machine Translation Robustness Task"}]},{"@id":"https://cir.nii.ac.jp/crid/1363670318634227456","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Enterprise resource planning survey of Swedish manufacturing firms"}]},{"@id":"https://cir.nii.ac.jp/crid/1363670320339859200","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Six Challenges for Neural Machine Translation"}]},{"@id":"https://cir.nii.ac.jp/crid/1363951793614264320","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Large-Scale, Diverse, Paraphrastic Bitexts via Sampling and Clustering"}]},{"@id":"https://cir.nii.ac.jp/crid/1363951793880125056","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Scaling Neural Machine Translation"}]},{"@id":"https://cir.nii.ac.jp/crid/1363951794605388928","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Data augmentation for low resource languages"}]},{"@id":"https://cir.nii.ac.jp/crid/1364233270606638080","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"BLEU"}]},{"@id":"https://cir.nii.ac.jp/crid/1390024091647684224","@type":"Article","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@language":"ja","@value":"LLM を用いたリランキングによる ERP ソフトウェア部品推薦システム"},{"@language":"en","@value":"Component Recommend System for Enterprise Resource Planning Package by Reranking using Large Language Models"}]},{"@id":"https://cir.nii.ac.jp/crid/1391975831220073728","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@language":"en","@value":"GiNZA - Practical Japanese NLP based on Universal Dependencies"},{"@language":"ja","@value":"GiNZA - Universal Dependencies による実用的日本語解析"},{"@language":"ja-Kana","@value":"GiNZA : Universal Dependencies ニ ヨル ジツヨウテキ ニホンゴ カイセキ"}]}],"dataSourceIdentifier":[{"@type":"JALC","@value":"oai:japanlinkcenter.org:2009028187"},{"@type":"CROSSREF","@value":"10.5715/jnlp.28.1270"},{"@type":"CIA","@value":"130008129477"},{"@type":"OPENAIRE","@value":"doi_________::d8aaf581ee76a441e4967cf90793e3c3"},{"@type":"CROSSREF","@value":"10.5715/jnlp.32.918_references_DOI_53Lcjz0KLjl9alRWEmsyxojQz8E"}]}