{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T07:37:03Z","timestamp":1765438623944,"version":"build-2065373602"},"reference-count":43,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2020,5,18]],"date-time":"2020-05-18T00:00:00Z","timestamp":1589760000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100009873","name":"Regione Autonoma della Sardegna","doi-asserted-by":"publisher","award":["CRP 120"],"award-info":[{"award-number":["CRP 120"]}],"id":[{"id":"10.13039\/501100009873","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003407","name":"Ministero dell\u2019Istruzione, dell\u2019Universit\u00e0 e della Ricerca","doi-asserted-by":"publisher","award":["PRIN 2017 Project HOPE"],"award-info":[{"award-number":["PRIN 2017 Project HOPE"]}],"id":[{"id":"10.13039\/501100003407","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>The hypernymy relation is the one occurring between an instance term and its general term (e.g., \u201clion\u201d and \u201canimal\u201d, \u201cItaly\u201d and \u201ccountry\u201d). This paper we addresses Hypernym Discovery, the NLP task that aims at finding valid hypernyms from words in a given text, proposing HyperRank, an unsupervised approach that therefore does not require manually-labeled training sets as most approaches in the literature. The proposed algorithm exploits the cosine distance of points in the vector space of word embeddings, as already proposed by previous state of the art approaches, but the ranking is then corrected by also weighting word frequencies and the absolute level of similarity, which is expected to be similar when measuring co-hyponyms and their common hypernym. This brings us two major advantages over other approaches\u2014(1) we correct the inadequacy of semantic similarity which is known to cause a significant performance drop and (2) we take into accounts multiple words if provided, allowing to find common hypernyms for a set of co-hyponyms\u2014a task ignored in other systems but very useful when coupled with set expansion (that finds co-hyponyms automatically). We then evaluate HyperRank against the SemEval 2018 Hypernym Discovery task and show that, regardless of the language or domain, our algorithm significantly outperforms all the existing unsupervised algorithms and some supervised ones as well. We also evaluate the algorithm on a new dataset to measure the improvements when finding hypernyms for sets of words instead of singletons.<\/jats:p>","DOI":"10.3390\/info11050268","type":"journal-article","created":{"date-parts":[[2020,5,18]],"date-time":"2020-05-18T11:34:14Z","timestamp":1589801654000},"page":"268","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Fully-Unsupervised Embeddings-Based Hypernym Discovery"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6112-7310","authenticated-orcid":false,"given":"Maurizio","family":"Atzori","sequence":"first","affiliation":[{"name":"DMI, University of Cagliari, 09124 Cagliari, Italy"}]},{"given":"Simone","family":"Balloccu","sequence":"additional","affiliation":[{"name":"Computing Science Department, University of Aberdeen, Aberdeen AB24 3FX, UK"}]}],"member":"1968","published-online":{"date-parts":[[2020,5,18]]},"reference":[{"key":"ref_1","unstructured":"Atzori, M. (2019, January 16\u201318). The Need of Structured Data: Introducing the OKgraph Project. Proceedings of the 10th Italian Information Retrieval Workshop, Padova, Italy."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Atzori, M., Balloccu, B., and Bellanti, A. (February, January 31). Unsupervised Singleton Expansion from Free Text. Proceedings of the 12th IEEE International Conference on Semantic Computing, ICSC 2018, Laguna Hills, CA, USA.","DOI":"10.1109\/ICSC.2018.00033"},{"key":"ref_3","unstructured":"Yu, Z., Wang, H., Lin, X., and Wang, M. (2015, January 25\u201331). Learning term embeddings for hypernymy identification. Proceedings of the 24th International Joint Conference on Artificial Intelligence, Buenos Aires, Argentina."},{"key":"ref_4","unstructured":"Seitner, J., Bizer, C., Eckert, K., Faralli, S., Meusel, R., Paulheim, H., and Ponzetto, S.P. (2016, January 23\u201328). A Large DataBase of Hypernymy Relations Extracted from the Web. Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC\u201916), Portoro\u017e, Slovenia."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.websem.2014.11.001","article-title":"Linked hypernyms: Enriching dbpedia with targeted hypernym discovery","volume":"31","author":"Kliegr","year":"2015","journal-title":"J. Web Sem."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Wang, C., He, X., and Zhou, A. (2017, January 7\u201311). A short survey on taxonomy learning from text corpora: Issues, resources and recent advances. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Copenhagen, Denmark.","DOI":"10.18653\/v1\/D17-1123"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Hearst, M.A. (1992, January 23\u201328). Automatic Acquisition of Hyponyms from Large Text Corpora. Proceedings of the 14th Conference on Computational Linguistics (COLING \u201992), Gothenburg, Sweden.","DOI":"10.3115\/992133.992154"},{"key":"ref_8","unstructured":"Snow, R., Jurafsky, D., and Ng, A.Y. (2004, January 13\u201318). Learning syntactic patterns for automatic hypernym discovery. Proceedings of the Neural Information Processing Systems Conference (NIPS 2004), Vancouver, BC, Canada."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Nguyen, K.A., K\u00f6per, M., Walde, S.S.i., and Vu, N.T. (2017). Hierarchical embeddings for hypernymy detection and directionality. arXiv.","DOI":"10.18653\/v1\/D17-1022"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Chang, H.S., Wang, Z., Vilnis, L., and McCallum, A. (2017). Distributional inclusion vector embedding for unsupervised hypernymy detection. arXiv.","DOI":"10.18653\/v1\/N18-1045"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Le, M., Roller, S., Papaxanthos, L., Kiela, D., and Nickel, M. (2019). Inferring concept hierarchies from text corpora via hyperbolic embeddings. arXiv.","DOI":"10.18653\/v1\/P19-1313"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"175693","DOI":"10.1109\/ACCESS.2019.2957827","article-title":"Detecting Hypernymy Relations Between Medical Compound Entities Using a Hybrid-Attention Based Bi-GRU-CapsNet Model","volume":"7","author":"Xu","year":"2019","journal-title":"IEEE Access"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Shwartz, V., Goldberg, Y., and Dagan, I. (2016). Improving hypernymy detection with an integrated path-based and distributional method. arXiv.","DOI":"10.18653\/v1\/P16-1226"},{"key":"ref_14","unstructured":"Ritter, A., Soderland, S., and Etzioni, O. (2009, January 23\u201325). What Is This, Anyway: Automatic Hypernym Discovery. Proceedings of the 2009 AAAI Spring Symposium: Learning by Reading and Learning to Read, Stanford, CA, USA."},{"key":"ref_15","unstructured":"Yates, A., Cafarella, M., Banko, M., Etzioni, O., Broadhead, M., and Soderland, S. Textrunner: Open information extraction on the web. Proceedings of the Human Language Technologies: The Annual Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations, Rochester, NY, USA."},{"key":"ref_16","unstructured":"Fu, R., Qin, B., and Liu, T. (2013, January 18\u201321). Exploiting multiple sources for open-domain hypernym discovery. Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, Seattle, WA, USA."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Yamada, I., Torisawa, K., Kazama, J., Kuroda, K., Murata, M., De Saeger, S., Bond, F., and Sumida, A. (2009, January 6\u20137). Hypernym discovery based on distributional similarity and hierarchical structures. Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, Singapore.","DOI":"10.3115\/1699571.1699634"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Espinosa-Anke, L., Camacho-Collados, J., Delli Bovi, C., and Saggion, H. (2016, January 1\u20135). Supervised distributional hypernym discovery via domain adaptation. Proceedings of the ACL Conference on Empirical Methods in Natural Language Processing, Austin, TX, USA.","DOI":"10.18653\/v1\/D16-1041"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Doval, Y., Camacho-Collados, J., Espinosa-Anke, L., and Schockaert, S. (2019). Meemi: A Simple Method for Post-processing Cross-lingual Word Embeddings. arXiv.","DOI":"10.18653\/v1\/P19-1318"},{"key":"ref_20","unstructured":"Palm Myllyl\u00e4, J. (2020, May 14). Domain Adaptation for Hypernym Discovery via Automatic Collection of Domain-Specific Training Data. Available online: http:\/\/www.diva-portal.org\/smash\/record.jsf?pid=diva2%3A1327273&dswid=1297."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Maldonado, A., and Klubi\u010dka, F. (2018, January 6\u20137). Adapt at semeval-2018 task 9: Skip-gram word embeddings for unsupervised hypernym discovery in specialised corpora. Proceedings of the 12th International Workshop on Semantic Evaluation, Minneapolis, MN, USA.","DOI":"10.18653\/v1\/S18-1151"},{"key":"ref_22","unstructured":"Aldine, A.I.A., Harzallah, M., Berio, G., B\u00e9chet, N., and Faour, A. (2018, January 6\u20137). EXPR at SemEval-2018 Task 9: A Combined Approach for Hypernym Discovery. Proceedings of the 12th International Workshop on Semantic Evaluation, Minneapolis, MN, USA."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Hassan, A.Z., Vallabhajosyula, M.S., and Pedersen, T. (2018). UMDuluth-CS8761 at SemEval-2018 Task 9: Hypernym Discovery using Hearst Patterns, Co-occurrence frequencies and Word Embeddings. arXiv.","DOI":"10.18653\/v1\/S18-1149"},{"key":"ref_24","unstructured":"Hashimoto, H., and Mori, S. (2019, January 7\u201313). LSTM Language Model for Hypernym Discovery. Proceedings of the 20th International Conference on Computational Linguistics and Intelligent Text Processing 2019, La Rochelle, France."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Plamada-Onofrei, M., Hulub, I., Trandabat, D., and G\u00eefu, D. (2018, January 6\u20137). Apollo at SemEval-2018 Task 9: Detecting Hypernymy Relations Using Syntactic Dependencies. Proceedings of the 12th International Workshop on Semantic Evaluation, Minneapolis, MN, USA.","DOI":"10.18653\/v1\/S18-1146"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Li, J., Zhao, H., and Tang, B. (2018). Sjtu-nlp at semeval-2018 task 9: Neural hypernym discovery with term embeddings. arXiv.","DOI":"10.18653\/v1\/S18-1147"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Dash, S., Chowdhury, M.F.M., Gliozzo, A., Mihindukulasooriya, N., and Fauceglia, N.R. (2020). Hypernym Detection Using Strict Partial Order Networks. arXiv.","DOI":"10.1609\/aaai.v34i05.6263"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Qiu, W., Chen, M., Li, L., and Si, L. (2018, January 6\u20137). NLP_HZ at SemEval-2018 Task 9: A Nearest Neighbor Approach. Proceedings of the 12th International Workshop on Semantic Evaluation, Minneapolis, MN, USA.","DOI":"10.18653\/v1\/S18-1148"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Berend, G., Makrai, M., and F\u00f6ldi\u00e1k, P. (2018, January 6\u20137). 300-sparsans at SemEval-2018 Task 9: Hypernymy as interaction of sparse attributes. Proceedings of the 12th International Workshop on Semantic Evaluation, Minneapolis, MN, USA.","DOI":"10.18653\/v1\/S18-1152"},{"key":"ref_30","unstructured":"Held, W., and Habash, N. (August, January 28). The Effectiveness of Simple Hybrid Systems for Hypernym Discovery. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy."},{"key":"ref_31","unstructured":"Aldine, A.I.A., Harzallah, M., Berio, G., Bechet, N., and Faour, A. (2019, January 22). Mining Sequential Patterns for Hypernym Relation Extraction. Proceedings of the TextMine\u201919, Metz, France."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Bernier-Colborne, G., and Barriere, C. (2018, January 6\u20137). CRIM at SemEval-2018 task 9: A hybrid approach to hypernym discovery. Proceedings of the 12th International Workshop on Semantic Evaluation, Minneapolis, MN, USA.","DOI":"10.18653\/v1\/S18-1116"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Shi, Y., Shen, J., Li, Y., Zhang, N., He, X., Lou, Z., Zhu, Q., Walker, M., Kim, M., and Han, J. (2019, January 3\u20137). Discovering Hypernymy in Text-Rich Heterogeneous Information Network by Exploiting Context Granularity. Proceedings of the 28th ACM International Conference on Information and Knowledge Management, Beijing China.","DOI":"10.1145\/3357384.3357866"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Shen, J., Shen, Z., Xiong, C., Wang, C., Wang, K., and Han, J. (2020, January 20\u201324). TaxoExpan: Self-supervised Taxonomy Expansion with Position-Enhanced Graph Neural Network. Proceedings of the Web Conference 2020, Taipei, Taiwan.","DOI":"10.1145\/3366423.3380132"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Luo, X., Liu, L., Yang, Y., Bo, L., Cao, Y., Wu, J., Li, Q., Yang, K., and Zhu, K.Q. (2020). AliCoCo: Alibaba E-commerce Cognitive Concept Net. arXiv.","DOI":"10.1145\/3318464.3386132"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Camacho-Collados, J., Delli Bovi, C., Espinosa-Anke, L., Oramas, S., Pasini, T., Santus, E., Shwartz, V., Navigli, R., and Saggion, H. (2018, January 5\u20136). SemEval-2018 task 9: Hypernym discovery. Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018), New Orleans, LA, USA.","DOI":"10.18653\/v1\/S18-1115"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Santus, E., Chiu, T.S., Lu, Q., Lenci, A., and Huang, C.R. (2016). Unsupervised measure of word similarity: How to outperform co-occurrence and vector cosine in vsms. arXiv.","DOI":"10.1609\/aaai.v30i1.9932"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1017\/S1351324910000124","article-title":"Directional distributional similarity for lexical inference","volume":"16","author":"Kotlerman","year":"2010","journal-title":"Nat. Lang. Eng."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Santus, E., Lenci, A., Lu, Q., and Im Walde, S.S. (2014, January 26\u201330). Chasing hypernyms in vector spaces with entropy. Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, Gothenburg, Sweden.","DOI":"10.3115\/v1\/E14-4008"},{"key":"ref_40","unstructured":"Han, L., and Finin, T. (2020, May 14). UMBC Webbase Corpus. Available online: http:\/\/ebiq.org\/r\/351."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1007\/s10579-009-9081-4","article-title":"The WaCky wide web: A collection of very large linguistically processed web-crawled corpora","volume":"43","author":"Baroni","year":"2009","journal-title":"Lang. Resour. Evaluat."},{"key":"ref_42","unstructured":"Cardellino, C. (2020, May 14). Spanish Billion Words Corpus And Embeddings. Available online: https:\/\/crscardellino.github.io\/SBWCE\/."},{"key":"ref_43","unstructured":"Calzolari, N., Choukri, K., Declerck, T., Goggi, S., Grobelnik, M., Maegaard, B., Mariani, J., Mazo, H., Moreno, A., and Odijk, J. (2016, January 23\u201328). ELMD: An automatically generated entity linking gold standard dataset in the music domain. Proceedings of the 10th International Conference on Language Resources and Evaluation LREC 2016, Portoroz, Slovenia."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/11\/5\/268\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T09:29:47Z","timestamp":1760174987000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/11\/5\/268"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,18]]},"references-count":43,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2020,5]]}},"alternative-id":["info11050268"],"URL":"https:\/\/doi.org\/10.3390\/info11050268","relation":{},"ISSN":["2078-2489"],"issn-type":[{"type":"electronic","value":"2078-2489"}],"subject":[],"published":{"date-parts":[[2020,5,18]]}}}