{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T11:15:20Z","timestamp":1730200520079,"version":"3.28.0"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,17]],"date-time":"2022-12-17T00:00:00Z","timestamp":1671235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,17]],"date-time":"2022-12-17T00:00:00Z","timestamp":1671235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,12,17]]},"DOI":"10.1109\/bigdata55660.2022.10020746","type":"proceedings-article","created":{"date-parts":[[2023,1,26]],"date-time":"2023-01-26T19:35:23Z","timestamp":1674761723000},"page":"4750-4757","source":"Crossref","is-referenced-by-count":0,"title":["Improving Model Performance Using Metric-Guided Data Selection Framework"],"prefix":"10.1109","author":[{"given":"Paulina Toro","family":"Isaza","sequence":"first","affiliation":[{"name":"IBM T.J. Watson Research Center,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Deng","sequence":"additional","affiliation":[{"name":"IBM T.J. Watson Research Center,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Nidd","sequence":"additional","affiliation":[{"name":"IBM Research Europe,Rüschlikon,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amar Prakash","family":"Azad","sequence":"additional","affiliation":[{"name":"IBM Research India,Bangalore,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laura","family":"Shwartz","sequence":"additional","affiliation":[{"name":"IBM T.J. Watson Research Center,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"1","key":"ref1","first-page":"11","article-title":"A data quality-driven view of MLOps","volume":"44","author":"Renggli","year":"2021","journal-title":"IEEE Data Engineering Bulletin"},{"key":"ref2","first-page":"38","article-title":"Word embeddings for the software engineering domain","volume-title":"Proceedings of the 15th International Conference on Mining Software Repositories","author":"Efstathiou"},{"key":"ref3","article-title":"Learning domain-specific word embeddings from sparse cybersecurity texts","volume-title":"CoRR","volume":"abs\/1709.07470","author":"Roy","year":"2017"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/ACCESS.2020.3032840"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/cloud53861.2021.00025"},{"key":"ref6","article-title":"Assessing the quality of natural language text data","author":"Sonntag","year":"2004","journal-title":"Informatik 2004\u2013Informatik verbindet\u2013Band 1, Beitr\u00e4ge der 34. Jahrestagung der Gesellschaft f\u00fcr Informatik eV (GI)"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1007\/978-3-319-12256-4_7"},{"key":"ref8","article-title":"A proposal to study \u201dis high quality data all we need?\"","volume-title":"arXiv preprint arXiv:2203.06404","author":"Mishra","year":"2022"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.3389\/fdata.2022.850611"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/InfRKM.2012.6204995"},{"key":"ref11","article-title":"Data quality toolkit: Automatic assessment of data quality and remediation for machine learning datasets","volume-title":"arXiv preprint arXiv:2108.05935","author":"Gupta","year":"2021"},{"key":"ref12","article-title":"Quality indicators for text data","author":"Kiefer","year":"2019","journal-title":"BTW 2019\u2013 Workshopband"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1145\/2669368"},{"key":"ref14","article-title":"DQI: Measuring data quality in nlp","author":"Mishra","year":"2020","journal-title":"arXiv preprint arXiv:2005.00816"},{"volume-title":"Proceedings of the 36 th International Conference on Machine Learning","author":"Ghadikolaei","article-title":"Learning and data selection in big datasets","key":"ref15"},{"key":"ref16","article-title":"Sub-setting algorithm for training data selection in pattern recognition","author":"Arwade","year":"2021","journal-title":"arXiv preprint arXiv:2110.06527"},{"volume-title":"International Conference on Learning Representations","author":"Coleman","article-title":"Selection via proxy: Efficient data selection for deep learning","key":"ref17"}],"event":{"name":"2022 IEEE International Conference on Big Data (Big Data)","start":{"date-parts":[[2022,12,17]]},"location":"Osaka, Japan","end":{"date-parts":[[2022,12,20]]}},"container-title":["2022 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10020192\/10020156\/10020746.pdf?arnumber=10020746","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T08:01:13Z","timestamp":1707811273000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10020746\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,17]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/bigdata55660.2022.10020746","relation":{},"subject":[],"published":{"date-parts":[[2022,12,17]]}}}