{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T20:28:39Z","timestamp":1758400119268,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":39,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819612413"},{"type":"electronic","value":"9789819612420"}],"license":[{"start":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T00:00:00Z","timestamp":1734048000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T00:00:00Z","timestamp":1734048000000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-1242-0_14","type":"book-chapter","created":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T08:05:35Z","timestamp":1733990735000},"page":"181-194","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Exploring the\u00a0Meaningfulness of\u00a0Nearest Neighbor Search in\u00a0High-Dimensional Space"],"prefix":"10.1007","author":[{"given":"Zhonghan","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiyuan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojun","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,13]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Amsaleg, L., et al.: Estimating local intrinsic dimensionality. In: SIGKDD, pp. 29\u201338. ACM (2015)","DOI":"10.1145\/2783258.2783405"},{"key":"14_CR2","unstructured":"Angiulli, F.: On the behavior of intrinsically high-dimensional spaces: distances, direct and reverse nearest neighbors, and hubness. J. Mach. Learn. Res. 18, 170:1\u2013170:60 (2017)"},{"key":"14_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2021.101807","volume":"101","author":"M Aum\u00fcller","year":"2021","unstructured":"Aum\u00fcller, M., Ceccarello, M.: The role of local dimensionality measures in benchmarking nearest neighbor search. Inf. Syst. 101, 101807 (2021)","journal-title":"Inf. Syst."},{"key":"14_CR4","unstructured":"Bornea, A., Ayed, F., Domenico, A.D., Piovesan, N., Maatouk, A.: Telco-rag: navigating the challenges of retrieval-augmented language models for telecommunications. CoRR abs\/2404.15939 (2024)"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Bowman, S.R., Angeli, G., Potts, C., Manning, C.D.: A large annotated corpus for learning natural language inference. In: M\u00e0rquez, L., Callison-Burch, C., Su, J. (eds.) Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (September 2015)","DOI":"10.18653\/v1\/D15-1075"},{"key":"14_CR6","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT, pp. 4171\u20134186. Association for Computational Linguistics (2019)"},{"key":"14_CR7","unstructured":"Es, S.: Orca-chat: a high-quality explanation-style chat dataset (2023). https:\/\/huggingface.co\/datasets\/shahules786\/orca-chat\/"},{"key":"14_CR8","unstructured":"Faysse, M., et al.: Croissantllm: a truly bilingual French-English language model (2024)"},{"key":"14_CR9","unstructured":"Gulli, A.: http:\/\/groups.di.unipi.it\/~gulli\/AG_corpus_of_news_articles.html"},{"key":"14_CR10","unstructured":"He, J., Kumar, S., Chang, S.: On the difficulty of nearest neighbor search. In: Proceedings of the 29th International Conference on Machine Learning, ICML 2012. icml.cc\/Omnipress (2012)"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Houle, M.E.: Dimensionality, discriminability, density and distance distributions. In: 13th IEEE International Conference on Data Mining Workshops, ICDM Workshops, pp. 468\u2013473. IEEE Computer Society (2013)","DOI":"10.1109\/ICDMW.2013.139"},{"key":"14_CR12","unstructured":"Huang, Y., Huang, J.: A survey on retrieval-augmented text generation for large language models. CoRR abs\/2404.10981 (2024)"},{"issue":"7","key":"14_CR13","doi-asserted-by":"publisher","first-page":"881","DOI":"10.1109\/TPAMI.2002.1017616","volume":"24","author":"T Kanungo","year":"2002","unstructured":"Kanungo, T., Mount, D.M., Netanyahu, N.S., Piatko, C.D., Silverman, R., Wu, A.Y.: An efficient k-means clustering algorithm: analysis and implementation. IEEE Trans. Pattern Anal. Mach. Intell. 24(7), 881\u2013892 (2002)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR14","unstructured":"Kim, J., et al.: Linq-embed-mistral: elevating text retrieval with improved gpt data through task-specific control and quality refinement. Linq AI Research Blog (2024). https:\/\/getlinq.com\/blog\/linq-embed-mistral\/"},{"key":"14_CR15","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS, pp. 1106\u20131114 (2012)"},{"key":"14_CR16","unstructured":"Le, Q.V., Mikolov, T.: Distributed representations of sentences and documents. In: ICML. JMLR Workshop and Conference Proceedings, vol.\u00a032, pp. 1188\u20131196. JMLR.org (2014)"},{"key":"14_CR17","unstructured":"Lee, C., et al.: NV-Embed: improved techniques for training llms as generalist embedding models. arXiv preprint arXiv:2405.17428 (2024)"},{"key":"14_CR18","unstructured":"Lewis, P.S.H., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. In: NeurIPS (2020)"},{"issue":"8","key":"14_CR19","doi-asserted-by":"publisher","first-page":"1475","DOI":"10.1109\/TKDE.2019.2909204","volume":"32","author":"W Li","year":"2020","unstructured":"Li, W., et al.: Approximate nearest neighbor search on high dimensional data - experiments, analyses, and improvement. IEEE Trans. Knowl. Data Eng. 32(8), 1475\u20131488 (2020)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"14_CR20","unstructured":"Li, Z., Zhang, X., Zhang, Y., Long, D., Xie, P., Zhang, M.: Towards general text embeddings with multi-stage contrastive learning. arXiv preprint arXiv:2308.03281 (2023)"},{"key":"14_CR21","unstructured":"Library, S.T.: https:\/\/huggingface.co\/datasets\/sentence-transformers\/gooaq"},{"key":"14_CR22","unstructured":"Library, S.T.: https:\/\/huggingface.co\/datasets\/sentence-transformers\/yahoo-answers\/viewer\/title-answer-pair"},{"issue":"4","key":"14_CR23","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1007\/BF01231606","volume":"3","author":"K Lin","year":"1994","unstructured":"Lin, K., Jagadish, H.V., Faloutsos, C.: The tv-tree: an index structure for high-dimensional data. VLDB J. 3(4), 517\u2013542 (1994)","journal-title":"VLDB J."},{"issue":"2","key":"14_CR24","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vis."},{"key":"14_CR25","unstructured":"McAuley, J.: https:\/\/huggingface.co\/datasets\/embedding-data\/Amazon-QA"},{"key":"14_CR26","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In: ICLR (Workshop Poster) (2013)"},{"key":"14_CR27","unstructured":"mnmoustafa, M.A.: Tiny imagenet (2017). https:\/\/kaggle.com\/competitions\/tiny-imagenet"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Muennighoff, N., Tazi, N., Magne, L., Reimers, N.: MTEB: massive text embedding benchmark. In: EACL, pp. 2006\u20132029. Association for Computational Linguistics (2023)","DOI":"10.18653\/v1\/2023.eacl-main.148"},{"key":"14_CR29","unstructured":"Neelakantan, A., et al.: Text and code embeddings by contrastive pre-training. CoRR abs\/2201.10005 (2022)"},{"issue":"3","key":"14_CR30","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1023\/A:1011139631724","volume":"42","author":"A Oliva","year":"2001","unstructured":"Oliva, A., Torralba, A.: Modeling the shape of the scene: a holistic representation of the spatial envelope. Int. J. Comput. Vis. 42(3), 145\u2013175 (2001)","journal-title":"Int. J. Comput. Vis."},{"key":"14_CR31","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 8748\u20138763. PMLR (2021)"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-bert: sentence embeddings using Siamese bert-networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (November 2019). http:\/\/arxiv.org\/abs\/1908.10084","DOI":"10.18653\/v1\/D19-1410"},{"key":"14_CR33","unstructured":"Scheepers, T.: Improving the Compositionality of Word Embeddings. Master\u2019s thesis, Universiteit van Amsterdam, Science Park 904, Amsterdam, Netherlands (November 2017)"},{"key":"14_CR34","doi-asserted-by":"crossref","unstructured":"Wang, W., Wei, F., Dong, L., Bao, H., Yang, N., Zhou, M.: Minilm: deep self-attention distillation for task-agnostic compression of pre-trained transformers. In: NeurIPS (2020)","DOI":"10.18653\/v1\/2021.findings-acl.188"},{"key":"14_CR35","unstructured":"Wikipedia: https:\/\/en.wikipedia.org\/wiki\/Curse_of_dimensionality"},{"key":"14_CR36","doi-asserted-by":"crossref","unstructured":"Williams, A., Nangia, N., Bowman, S.: A broad-coverage challenge corpus for sentence understanding through inference. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) (2018)","DOI":"10.18653\/v1\/N18-1101"},{"key":"14_CR37","doi-asserted-by":"crossref","unstructured":"Xiao, S., Liu, Z., Zhang, P., Muennighoff, N.: C-pack: packaged resources to advance general chinese embedding (2023)","DOI":"10.1145\/3626772.3657878"},{"key":"14_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, X., et\u00a0al.: MGTE: generalized long-context text representation and reranking models for multilingual text retrieval. arXiv preprint arXiv:2407.19669 (2024)","DOI":"10.18653\/v1\/2024.emnlp-industry.103"},{"key":"14_CR39","doi-asserted-by":"crossref","unstructured":"Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., Torralba, A.: Places: a 10 million image database for scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2017)","DOI":"10.1167\/17.10.296"}],"container-title":["Lecture Notes in Computer Science","Databases Theory and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-1242-0_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,6]],"date-time":"2025-01-06T20:04:05Z","timestamp":1736193845000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-1242-0_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,13]]},"ISBN":["9789819612413","9789819612420"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-1242-0_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,13]]},"assertion":[{"value":"13 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ADC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australasian Database Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Gold Coast, QLD","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"35","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"adc2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/adc-conference.github.io\/2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}