{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,5]],"date-time":"2026-09-05T05:17:14Z","timestamp":1788585434174,"version":"build-2803163510"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"15","license":[{"start":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T00:00:00Z","timestamp":1785456000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T00:00:00Z","timestamp":1785456000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1007\/s00521-026-12342-2","type":"journal-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T05:47:53Z","timestamp":1785476873000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A data-centric analysis for efficient semantic knowledge acquisition in word embeddings"],"prefix":"10.1007","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8082-4833","authenticated-orcid":false,"given":"Aishwarya","family":"Jadhav","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Anderson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jose","family":"Camacho-Collados","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zachary","family":"Pardos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"12342_CR1","unstructured":"Mikolov T, Yih W-t, Zweig G (2013) Linguistic regularities in continuous space word representations. In: Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp 746\u2013751"},{"key":"12342_CR2","unstructured":"Bordes A, Usunier N, Garcia-Duran A, Weston J, Yakhnenko O (2013) Translating embeddings for modeling multi-relational data. Adv Neural Inf Process Syst 26"},{"issue":"4","key":"12342_CR3","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1109\/TASLP.2016.2520371","volume":"24","author":"H Palangi","year":"2016","unstructured":"Palangi H, Deng L, Shen Y, Gao J, He X, Chen J, Song X, Ward R (2016) Deep sentence embedding using long short-term memory networks: analysis and application to information retrieval. IEEE ACM Trans Audio Speech Lang Process 24(4):694\u2013707","journal-title":"IEEE ACM Trans Audio Speech Lang Process"},{"key":"12342_CR4","doi-asserted-by":"crossref","unstructured":"Finley G, Farmer S, Pakhomov S (2017) What analogies reveal about word vectors and their compositionality. In: Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017), pp 1\u201311","DOI":"10.18653\/v1\/S17-1001"},{"key":"12342_CR5","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1146\/annurev-linguistics-030514-125254","volume":"4","author":"A Lenci","year":"2018","unstructured":"Lenci A (2018) Distributional models of word meaning. Annual Rev Linguistics 4:151\u2013171","journal-title":"Annual Rev Linguistics"},{"key":"12342_CR6","doi-asserted-by":"crossref","unstructured":"Jadhav A, Amir Y, Pardos Z (2020) Lexical relation mining in neural word embeddings. In: Proceedings of the 28th International Conference on Computational Linguistics, pp 1299\u20131311","DOI":"10.18653\/v1\/2020.coling-main.112"},{"key":"12342_CR7","doi-asserted-by":"crossref","unstructured":"Ushio A, Espinosa-Anke L, Schockaert S, Camacho-Collados J (2021) Bert is to nlp what alexnet is to cv: can pre-trained language models identify analogies? arXiv preprint arXiv:2105.04949","DOI":"10.18653\/v1\/2021.acl-long.280"},{"key":"12342_CR8","unstructured":"Mikolov T, Chen K, Corrado G, Dean J (2013) Efficient estimation of word representations in vector space. arXiv preprint arXiv:13013781"},{"key":"12342_CR9","unstructured":"Coleman C, Yeh C, Mussmann S, Mirzasoleiman B, Bailis P, Liang P, Leskovec J, Zaharia M (2019) Selection via proxy: Efficient data selection for deep learning. arXiv preprint arXiv:1906.11829"},{"key":"12342_CR10","doi-asserted-by":"crossref","unstructured":"Xie SM, Santurkar S, Ma T, Liang P (2023) Data selection for language models via importance resampling. arXiv preprint arXiv :230203169","DOI":"10.52202\/075280-1482"},{"key":"12342_CR11","doi-asserted-by":"crossref","unstructured":"Yu Z, Das S, Xiong C (2024) MATES: Model-aware data selection for efficient pretraining with data influence models. In: Advances in Neural Information Processing Systems (NeurIPS)","DOI":"10.52202\/079017-3453"},{"key":"12342_CR12","unstructured":"Koh PW, Liang P (2017) Understanding black-box predictions via influence functions. In: International Conference on Machine Learning, pp 1885\u20131894 PMLR"},{"key":"12342_CR13","first-page":"19920","volume":"33","author":"G Pruthi","year":"2020","unstructured":"Pruthi G, Liu F, Kale S, Sundararajan M (2020) Estimating training data influence by tracing gradient descent. Adv Neural Inf Process Syst 33:19920\u201319930","journal-title":"Adv Neural Inf Process Syst"},{"key":"12342_CR14","first-page":"20596","volume":"34","author":"M Paul","year":"2021","unstructured":"Paul M, Ganguli S, Dziugaite GK (2021) Deep learning on a data diet: Finding important examples early in training. Adv Neural Inf Process Syst 34:20596\u201320607","journal-title":"Adv Neural Inf Process Syst"},{"key":"12342_CR15","unstructured":"Toneva M, Sordoni A, Combes RTd, Trischler A, Bengio Y, Gordon GJ (2018) An empirical study of example forgetting during deep neural network learning. arXiv preprint arXiv :181205159"},{"key":"12342_CR16","unstructured":"Grosse R, Bae J, Anil C, Elhage N, Tamkin A, Tajdini A, Steiner B, Li D, Durmus E, Perez E et al (2023) Studying large language model generalization with influence functions. arXiv preprint arXiv :230803296"},{"key":"12342_CR17","doi-asserted-by":"crossref","unstructured":"Ribeiro MT, Singh S, Guestrin C (2016) why should i trust you? explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp 1135\u20131144","DOI":"10.1145\/2939672.2939778"},{"key":"12342_CR18","unstructured":"Lundberg SM, Lee S-I (2017) A unified approach to interpreting model predictions. Adv Neural Inf Process Syst 30"},{"key":"12342_CR19","doi-asserted-by":"publisher","first-page":"19523","DOI":"10.52202\/068431-1419","volume":"35","author":"B Sorscher","year":"2022","unstructured":"Sorscher B, Geirhos R, Shekhar S, Ganguli S, Morcos A (2022) Beyond neural scaling laws: beating power law scaling via data pruning. Adv Neural Inf Process Syst 35:19523\u201319536","journal-title":"Adv Neural Inf Process Syst"},{"key":"12342_CR20","doi-asserted-by":"crossref","unstructured":"Aky\u00fcrek E, Bolukbasi T, Liu F, Xiong B, Tenney I, Andreas J, Guu K (2022) Towards tracing knowledge in language models back to the training data. In: Findings of the Association for Computational Linguistics: EMNLP 2022, pp 2429\u20132446","DOI":"10.18653\/v1\/2022.findings-emnlp.180"},{"key":"12342_CR21","doi-asserted-by":"crossref","unstructured":"Rajani NF, McCann B, Xiong C, Socher R (2019) Explain yourself! leveraging language models for commonsense reasoning. arXiv preprint arXiv:1906.02361","DOI":"10.18653\/v1\/P19-1487"},{"key":"12342_CR22","unstructured":"Brunet M-E, Alkalay-Houlihan C, Anderson A, Zemel R (2019) Understanding the origins of bias in word embeddings. In: International Conference on Machine Learning, pp. 803\u2013811 PMLR"},{"key":"12342_CR23","doi-asserted-by":"crossref","unstructured":"Van Der Wal O, Jumelet J, Schulz K, Zuidema W (2022) The birth of bias: A case study on the evolution of gender bias in an english language model. arXiv preprint arXiv :220710245","DOI":"10.18653\/v1\/2022.gebnlp-1.8"},{"key":"12342_CR24","unstructured":"Albalak A, Elazar Y, Xie SM, Longpre S, Lambert N, Wang X, Muennighoff N et al (2024) A survey on data selection for language models. Trans Mach Learn Res arXiv:2402.16827"},{"key":"12342_CR25","unstructured":"Deng Z, Li T, Li Y (2024) Influential language data selection via gradient trajectory pursuit. arXiv preprint arXiv :241016710"},{"key":"12342_CR26","unstructured":"Wettig A, Gupta A, Malik S, Chen D (2024) QuRating: Selecting high-quality data for training language models. In: International Conference on Machine Learning (ICML) arXiv:2402.09739"},{"key":"12342_CR27","doi-asserted-by":"crossref","unstructured":"Brandfonbrener D, Zhang H, Kirsch A, Schwarz JR, Kakade S (2024) CoLoR-Filter: Conditional loss reduction filtering for targeted language model pre-training. In: Advances in Neural Information Processing Systems (NeurIPS)","DOI":"10.52202\/079017-3097"},{"key":"12342_CR28","doi-asserted-by":"publisher","unstructured":"Camacho-Collados J, Pilehvar MT, Navigli R (2015) A framework for the construction of monolingual and cross-lingual word similarity datasets. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pp. 1\u20137. Association for Computational Linguistics, Beijing, China https:\/\/doi.org\/10.3115\/v1\/P15-2001. https:\/\/aclanthology.org\/P15-2001","DOI":"10.3115\/v1\/P15-"},{"key":"12342_CR29","unstructured":"Joulin A, Grave E, Bojanowski P, Mikolov T (2016) Bag of tricks for efficient text classification. arXiv preprint arXiv :160701759"},{"key":"12342_CR30","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning CD (2014) Glove: Global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 1532\u20131543","DOI":"10.3115\/v1\/D14-1162"},{"key":"12342_CR31","unstructured":"Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Levy O, Lewis M, Zettlemoyer L, Stoyanov V (2019) Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692"},{"key":"12342_CR32","doi-asserted-by":"publisher","unstructured":"Ben Zaken E, Goldberg Y, Ravfogel S (2022) BitFit: Simple parameter-efficient fine-tuning for transformer-based masked language-models. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 1\u20139. Association for Computational Linguistics, Dublin, Ireland. https:\/\/doi.org\/10.18653\/v1\/2022.acl-short.1. https:\/\/aclanthology.org\/2022.acl-short.1","DOI":"10.18653\/v1\/2022.acl-short.1."},{"key":"12342_CR33","doi-asserted-by":"publisher","unstructured":"Faruqui M, Tsvetkov Y, Rastogi P, Dyer C (2016) Problems with evaluation of word embeddings using word similarity tasks. In: Proceedings of the 1st Workshop on Evaluating Vector-Space Representations for NLP, pp. 30\u201335. Association for Computational Linguistics, Berlin, Germany https:\/\/doi.org\/10.18653\/v1\/W16-2506. https:\/\/aclanthology.org\/W16-2506","DOI":"10.18653\/v1\/W16-2506"},{"key":"12342_CR34","doi-asserted-by":"publisher","unstructured":"Linzen T (2016) Issues in evaluating semantic spaces using word analogies. In: Proceedings of the 1st Workshop on Evaluating Vector-Space Representations for NLP, pp. 13\u201318. Association for Computational Linguistics, Berlin, Germany https:\/\/doi.org\/10.18653\/v1\/W16-2503. https:\/\/aclanthology.org\/W16-2503","DOI":"10.18653\/v1\/W16-2503"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-026-12342-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-026-12342-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-026-12342-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,5]],"date-time":"2026-09-05T04:49:09Z","timestamp":1788583749000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-026-12342-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,31]]},"references-count":34,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["12342"],"URL":"https:\/\/doi.org\/10.1007\/s00521-026-12342-2","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,31]]},"assertion":[{"value":"7 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare that they have no conflict of interest.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"606"}}