{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T03:41:58Z","timestamp":1778125318817,"version":"3.51.4"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031789762","type":"print"},{"value":"9783031789779","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-78977-9_7","type":"book-chapter","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T10:11:55Z","timestamp":1737972715000},"page":"101-115","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["AutoML-Guided Fusion of\u00a0Entity and\u00a0LLM-Based Representations for\u00a0Document Classification"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7330-0579","authenticated-orcid":false,"given":"Boshko","family":"Koloski","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4380-0863","authenticated-orcid":false,"given":"Senja","family":"Pollak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3831-9706","authenticated-orcid":false,"given":"Roberto","family":"Navigli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9916-8756","authenticated-orcid":false,"given":"Bla\u017e","family":"\u0160krlj","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,28]]},"reference":[{"key":"7_CR1","unstructured":"AI@Meta: Llama 3 model card (2024)"},{"issue":"6","key":"7_CR2","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1038\/s41592-018-0019-x","volume":"15","author":"N Altman","year":"2018","unstructured":"Altman, N., Krzywinski, M.: The curse (s) of dimensionality. Nat. Methods 15(6), 399\u2013400 (2018)","journal-title":"Nat. Methods"},{"key":"7_CR3","unstructured":"BehnamGhader, P., Adlakha, V., Mosbach, M., Bahdanau, D., Chapados, N., Reddy, S.: LLM2Vec: large language models are secretly powerful text encoders. arXiv preprint (2024). https:\/\/arxiv.org\/abs\/2404.05961"},{"issue":"8","key":"7_CR4","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","volume":"35","author":"Y Bengio","year":"2013","unstructured":"Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798\u20131828 (2013). https:\/\/doi.org\/10.1109\/TPAMI.2013.50","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"6","key":"7_CR5","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9","volume":"41","author":"S Deerwester","year":"1990","unstructured":"Deerwester, S., Dumais, S.T., Furnas, G.W., Landauer, T.K., Harshman, R.: Indexing by latent semantic analysis. J. Am. Soc. Inf. Sci. 41(6), 391\u2013407 (1990)","journal-title":"J. Am. Soc. Inf. Sci."},{"key":"7_CR6","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Gao, T., Fisch, A., Chen, D.: Making pre-trained language models better few-shot learners. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 3816\u20133830 (2021)","DOI":"10.18653\/v1\/2021.acl-long.295"},{"key":"7_CR8","doi-asserted-by":"publisher","unstructured":"Hernandez, E., Andreas, J.: The low-dimensional linear geometry of contextualized word representations. In: Bisazza, A., Abend, O. (eds.) Proceedings of the 25th Conference on Computational Natural Language Learning, pp. 82\u201393. Association for Computational Linguistics, Online (2021). https:\/\/doi.org\/10.18653\/v1\/2021.conll-1.7. https:\/\/aclanthology.org\/2021.conll-1.7","DOI":"10.18653\/v1\/2021.conll-1.7"},{"issue":"1","key":"7_CR9","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1109\/TIT.1968.1054102","volume":"14","author":"G Hughes","year":"1968","unstructured":"Hughes, G.: On the mean accuracy of statistical pattern recognizers. IEEE Trans. Inf. Theory 14(1), 55\u201363 (1968). https:\/\/doi.org\/10.1109\/TIT.1968.1054102","journal-title":"IEEE Trans. Inf. Theory"},{"key":"7_CR10","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1016\/j.neucom.2022.01.096","volume":"496","author":"B Koloski","year":"2022","unstructured":"Koloski, B., Perdih, T.S., Robnik-\u0160ikonja, M., Pollak, S., \u0160krlj, B.: Knowledge graph informed fake news classification via heterogeneous representation ensembles. Neurocomputing 496, 208\u2013226 (2022)","journal-title":"Neurocomputing"},{"key":"7_CR11","unstructured":"Koloski, B., Pollak, S., Skrlj, B.: Multilingual detection of fake news spreaders via sparse matrix factorization. In: CLEF (Working Notes) (2020)"},{"key":"7_CR12","unstructured":"Koloski, B., \u0160krlj, B., Pollak, S., Lavra\u010d, N.: Latent graph powered semi-supervised learning on biomedical tabular data. arXiv preprint arXiv:2309.15757 (2023)"},{"key":"7_CR13","unstructured":"Kuzman, T., Rupnik, P., Ljube\u0161i\u0107, N.: The GINCO training dataset for web genre identification of documents out in the wild. In: Calzolari, N., et al. (eds.) Proceedings of the Thirteenth Language Resources and Evaluation Conference, pp. 1584\u20131594. European Language Resources Association, Marseille, France (2022). https:\/\/aclanthology.org\/2022.lrec-1.170"},{"key":"7_CR14","unstructured":"Le, Q., Mikolov, T.: Distributed representations of sentences and documents. In: International Conference on Machine Learning, pp. 1188\u20131196. PMLR (2014)"},{"issue":"1","key":"7_CR15","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1093\/bioinformatics\/btz470","volume":"36","author":"TT Le","year":"2020","unstructured":"Le, T.T., Fu, W., Moore, J.H.: Scaling tree-based automated machine learning to biomedical big data with a feature set selector. Bioinformatics 36(1), 250\u2013256 (2020)","journal-title":"Bioinformatics"},{"key":"7_CR16","doi-asserted-by":"publisher","first-page":"193907","DOI":"10.1109\/ACCESS.2020.3031549","volume":"8","author":"PH Le-Khac","year":"2020","unstructured":"Le-Khac, P.H., Healy, G., Smeaton, A.F.: Contrastive representation learning: a framework and review. IEEE Access 8, 193907\u2013193934 (2020)","journal-title":"IEEE Access"},{"key":"7_CR17","unstructured":"Li, X., Li, J.: Angle-optimized text embeddings. arXiv preprint arXiv:2309.12871 (2023)"},{"key":"7_CR18","unstructured":"Lin, Z., Wang, B., Liu, Y., et\u00a0al.: Chatqa: building GPT-4 level conversational QA models. arXiv preprint arXiv:2301.12345 (2023)"},{"key":"7_CR19","doi-asserted-by":"publisher","unstructured":"Moro, A., Raganato, A., Navigli, R.: Entity linking meets word sense disambiguation: a unified approach. Trans. Assoc. Comput. Linguist. 2, 231\u2013244 (2014). https:\/\/doi.org\/10.1162\/tacl_a_00179. https:\/\/aclanthology.org\/Q14-1019","DOI":"10.1162\/tacl_a_00179"},{"key":"7_CR20","doi-asserted-by":"publisher","unstructured":"Muennighoff, N., Tazi, N., Magne, L., Reimers, N.: MTEB: massive text embedding benchmark. In: Vlachos, A., Augenstein, I. (eds.) Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pp. 2014\u20132037. Association for Computational Linguistics, Dubrovnik, Croatia (2023). https:\/\/doi.org\/10.18653\/v1\/2023.eacl-main.148. https:\/\/aclanthology.org\/2023.eacl-main.148","DOI":"10.18653\/v1\/2023.eacl-main.148"},{"key":"7_CR21","unstructured":"Navigli, R., Ponzetto, S.P.: BabelNet: building a very large multilingual semantic network. In: Haji\u010d, J., Carberry, S., Clark, S., Nivre, J. (eds.) Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pp. 216\u2013225. Association for Computational Linguistics, Uppsala, Sweden (2010). https:\/\/aclanthology.org\/P10-1023"},{"key":"7_CR22","unstructured":"Ostendorff, M., Bourgonje, P., Berger, M., Moreno-Schneider, J., Rehm, G., Gipp, B.: Enriching bert with knowledge graph embeddings for document classification. arXiv preprint arXiv:1909.08402 (2019)"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Pan, S., Luo, L., Wang, Y., Chen, C., Wang, J., Wu, X.: Unifying large language models and knowledge graphs: a roadmap. IEEE Trans. Knowl. Data Eng. 36, 3580\u20133599 (2023). https:\/\/api.semanticscholar.org\/CorpusID:259165563","DOI":"10.1109\/TKDE.2024.3352100"},{"key":"7_CR24","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"7_CR25","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners (2019). https:\/\/www.semanticscholar.org\/paper\/Language-Models-are-Unsupervised-Multitask-Learners-Radford-Wu\/9405cc0d6169988371b2755e573cc28650d14dfe"},{"key":"7_CR26","doi-asserted-by":"publisher","unstructured":"Ranasinghe, T., Zampieri, M.: Multilingual offensive language identification with cross-lingual embeddings. In: Webber, B., Cohn, T., He, Y., Liu, Y. (eds.) Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 5838\u20135844. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.470. https:\/\/aclanthology.org\/2020.emnlp-main.470","DOI":"10.18653\/v1\/2020.emnlp-main.470"},{"key":"7_CR27","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 (2019). https:\/\/arxiv.org\/abs\/1908.10084","DOI":"10.18653\/v1\/D19-1410"},{"key":"7_CR28","unstructured":"Schwenk, H., Li, X.: A corpus for multilingual document classification in eight languages. In: Chair, N.C.C., et al. (eds.) Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018). European Language Resources Association (ELRA), Paris, France (2018)"},{"key":"7_CR29","unstructured":"Sean, L., Aamir, S., Darius, K., Julius, L.: Open source strikes bread - new fluffy embeddings model (2024). https:\/\/www.mixedbread.ai\/blog\/mxbai-embed-large-v1"},{"key":"7_CR30","doi-asserted-by":"publisher","unstructured":"\u0160krlj, B., Martinc, M., Lavra\u010d, N., Pollak, S.: autoBOT: evolving neuro-symbolic representations for explainable low resource text classification. Mach. Learn. (2021). https:\/\/doi.org\/10.1007\/s10994-021-05968-x","DOI":"10.1007\/s10994-021-05968-x"},{"key":"7_CR31","unstructured":"Sun, Z., Deng, Z.H., Nie, J.Y., Tang, J.: Rotate: knowledge graph embedding by relational rotation in complex space. arXiv preprint arXiv:1902.10197 (2019)"},{"key":"7_CR32","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"7_CR33","doi-asserted-by":"publisher","unstructured":"Vrande\u010di\u0107, D., Kr\u00f6tzsch, M.: Wikidata: a free collaborative knowledgebase. Commun. ACM 57(10), 78\u201385 (2014). https:\/\/doi.org\/10.1145\/2629489","DOI":"10.1145\/2629489"},{"key":"7_CR34","doi-asserted-by":"publisher","unstructured":"Wolf, T., et al.: Transformers: state-of-the-art natural language processing. In: Liu, Q., Schlangen, D. (eds.) Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38\u201345. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-demos.6. https:\/\/aclanthology.org\/2020.emnlp-demos.6","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"7_CR35","unstructured":"Zhao, W.X., et al.: A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Xu, S., Tang, J., Qu, M.: Graphvite: a high-performance CPU-GPU hybrid system for node embedding. In: The World Wide Web Conference, pp. 2494\u20132504 (2019)","DOI":"10.1145\/3308558.3313508"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Zosa, E., Boro\u015f, E., Koloski, B., Pivovarova, L.: Embeddia at semeval-2022 task 8: investigating sentence, image, and knowledge graph representations for multilingual news article similarity. In: Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pp. 1107\u20131113 (2022)","DOI":"10.18653\/v1\/2022.semeval-1.156"},{"key":"7_CR38","doi-asserted-by":"publisher","unstructured":"\u0160krlj, B., Petkovi\u0107, M.: Compressibility of distributed document representations. In: 2021 IEEE International Conference on Data Mining (ICDM), pp. 1330\u20131335 (2021). https:\/\/doi.org\/10.1109\/ICDM51629.2021.00166","DOI":"10.1109\/ICDM51629.2021.00166"}],"container-title":["Lecture Notes in Computer Science","Discovery Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78977-9_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T10:12:28Z","timestamp":1737972748000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78977-9_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031789762","9783031789779"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78977-9_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"28 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Discovery Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pisa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"14 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dis2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ds2024.isti.cnr.it\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}