{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T17:27:13Z","timestamp":1790270833612,"version":"4.1.0"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,7]]},"abstract":"<jats:p>Distributed word embeddings have shown superior performances in numerous Natural Language Processing (NLP) tasks.\n\nHowever, their performances vary significantly across different tasks,\n\nimplying that the word embeddings learnt by those methods capture complementary aspects of lexical semantics.\n\nTherefore, we believe that it is important to combine the existing word embeddings to produce more accurate and complete\n\nmeta-embeddings of words.\n\nFor this purpose, we propose an unsupervised locally linear meta-embedding learning method that takes \n\npre-trained word embeddings as the input, and produces more accurate meta embeddings.\n\nUnlike previously proposed meta-embedding learning methods that learn a global projection over all words in a vocabulary,\n\nour proposed method is sensitive to the differences in local neighbourhoods of the individual source word embeddings. \n\nMoreover, we show that vector concatenation, a previously proposed highly competitive baseline\n\napproach for integrating word embeddings, can be derived as a special case of the proposed method.\n\nExperimental results on semantic similarity, word analogy, relation classification, and short-text classification tasks show that our\n\nmeta-embeddings to significantly outperform prior methods in several benchmark datasets,\n\nestablishing a new state of the art for meta-embeddings.<\/jats:p>","DOI":"10.24963\/ijcai.2018\/552","type":"proceedings-article","created":{"date-parts":[[2018,7,5]],"date-time":"2018-07-05T01:49:10Z","timestamp":1530755350000},"page":"3970-3976","source":"Crossref","is-referenced-by-count":11,"title":["Think Globally, Embed Locally --- Locally Linear Meta-embedding of Words"],"prefix":"10.24963","author":[{"given":"Danushka","family":"Bollegala","sequence":"first","affiliation":[{"name":"University of Liverpool, Liverpool, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kohei","family":"Hayashi","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ken-ichi","family":"Kawarabayashi","sequence":"additional","affiliation":[{"name":"National Institute of Informatics, Japan Science and Technology Agency, ERATO, Kawarabayashi Large Graph Project"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10584","event":{"name":"Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18}","theme":"Artificial Intelligence","location":"Stockholm, Sweden","acronym":"IJCAI-2018","number":"27","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2018,7,13]]},"end":{"date-parts":[[2018,7,19]]}},"container-title":["Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2018,7,5]],"date-time":"2018-07-05T01:53:51Z","timestamp":1530755631000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2018\/552"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2018\/552","relation":{},"subject":[],"published":{"date-parts":[[2018,7]]}}}