{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T10:44:59Z","timestamp":1773917099656,"version":"3.50.1"},"reference-count":20,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["22K12145"],"award-info":[{"award-number":["22K12145"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100018205","name":"National Institute for Japanese Language and Linguistics","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018205","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Data & Knowledge Engineering"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1016\/j.datak.2025.102537","type":"journal-article","created":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T17:24:13Z","timestamp":1765560253000},"page":"102537","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["All-words pronunciation estimation of Japanese homographs"],"prefix":"10.1016","volume":"162","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6405-1067","authenticated-orcid":false,"given":"Kanako","family":"Komiya","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taichiro","family":"Kobayashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5178-7275","authenticated-orcid":false,"given":"Masayuki","family":"Asahara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7772-4985","authenticated-orcid":false,"given":"Hiroyuki","family":"Shinnou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.datak.2025.102537_b1","unstructured":"T. Kobayashi, K. Komiya, SVM wo mochiita BCCWJ ni okeru douonigigo no yomisuitei. [Pronounciation Estimation of Monographs of BCCWJ Using SVM], in: Proceedings of the NLP2021, (in Japanese), 2021, pp. 405\u2013409,."},{"key":"10.1016\/j.datak.2025.102537_b2","series-title":"Proceedings of the Thirteenth Language Resources and Evaluation Conference","first-page":"7113","article-title":"Building large-scale Japanese pronunciation-annotated corpora for reading heteronymous logograms","author":"Sato","year":"2022"},{"key":"10.1016\/j.datak.2025.102537_b3","series-title":"Proceedings of the Workshop on Computation and Written Language","first-page":"50","article-title":"Pronunciation ambiguities in Japanese kanji","author":"Zhang","year":"2023"},{"key":"10.1016\/j.datak.2025.102537_b4","series-title":"NLP2023 Workshop on Japanese Language Resources (JLR2023) of the 29th Annual Meeting of the Association for Natural Language Processing","article-title":"Data processing for Japanese text-to-pronciation models","author":"Mazovetskiy","year":"2023"},{"issue":"2","key":"10.1016\/j.datak.2025.102537_b5","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1007\/s10579-013-9261-0","article-title":"Balanced corpus of contemporary written Japanese","volume":"48","author":"Maekawa","year":"2014","journal-title":"Lang. Resour. Eval."},{"issue":"5","key":"10.1016\/j.datak.2025.102537_b6","doi-asserted-by":"crossref","first-page":"705","DOI":"10.5715\/jnlp.24.705","article-title":"nwjc2vec: Word embedding data constructed from NINGAL web Japanese corpus","volume":"24","author":"Shinnou","year":"2017","journal-title":"J. Nat. Lang. Process."},{"key":"10.1016\/j.datak.2025.102537_b7","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.datak.2025.102537_b8","series-title":"Proceedings of the 30th Meeting of Japanese Natural Language Processing","first-page":"1847","article-title":"Attempt to construct a speech corpus with annotations of aozora bunko furigana using speech recognition [onsei ninshiki o mochiita aosorabunko furigana ch\u016bshaku-tsuki onsei k\u014dpasu no k\u014dchiku no kokoromi]","author":"Sato","year":"2024"},{"key":"10.1016\/j.datak.2025.102537_b9","unstructured":"K. Maekawa, Corpus of Spontaneous Japanese: Its design and evaluation, in: ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition, 2003."},{"issue":"2","key":"10.1016\/j.datak.2025.102537_b10","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1016\/j.datak.2007.03.013","article-title":"Combining classifiers for word sense disambiguation based on Dempster\u2013Shafer theory and OWA operators","volume":"63","author":"Le","year":"2007","journal-title":"Data Knowl. Eng."},{"key":"10.1016\/j.datak.2025.102537_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.datak.2022.102077","article-title":"Combining specialized word embeddings and subword semantic features for lexical entailment recognition","volume":"141","author":"Bui","year":"2022","journal-title":"Data Knowl. Eng."},{"key":"10.1016\/j.datak.2025.102537_b12","series-title":"Proceedings of the 31st Pacific Asia Conference on Language, Information and Computation","first-page":"392","article-title":"Japanese all-words WSD system using the kyoto text analysis ToolKit","author":"Shinnou","year":"2017"},{"issue":"2","key":"10.1016\/j.datak.2025.102537_b13","doi-asserted-by":"crossref","first-page":"361","DOI":"10.5715\/jnlp.26.361","article-title":"Unsupervised all-wrods WSD using synonyms and embeddings","volume":"26","author":"Suzuki","year":"2019","journal-title":"J. Nat. Lang. Process."},{"key":"10.1016\/j.datak.2025.102537_b14","series-title":"Using BERT for word sense disambiguation","author":"Du","year":"2019"},{"key":"10.1016\/j.datak.2025.102537_b15","series-title":"Proceedings of the 37th Pacific Asia Conference on Language, Information and Computation","first-page":"201","article-title":"All-words word sense disambiguation for historical Japanese","author":"Asada","year":"2023"},{"key":"10.1016\/j.datak.2025.102537_b16","unstructured":"S. Kiyono, J. Suzuki, M. Mita, T. Mizumoto, K. Inui, Daikibo gizi deta wo mochiita kouseinou ayamari teisei moderu no kouciku [Building a high-performance grammar error correction model using large-scale pseudo-data], in: Proceedings of NLP 2020, 2020, pp. 989\u2013992, in Japanese."},{"key":"10.1016\/j.datak.2025.102537_b17","unstructured":"I. Saito, J. Suzuki, K. Sadamitsu, K. Nishida, K. Saito, Y. Saito, Giji deta no zizengakusyu ni motoduku encoder-decoder gata nihongokuzure hyoukiseikika [Encoder-decoder type Japanese collapsed notation normalisation based on pre-training of pseudo-data], in: Proceedings of NLP 2017, 2017, pp. 585\u2013588, in Japanese."},{"key":"10.1016\/j.datak.2025.102537_b18","series-title":"International Conference on Natural Language Processing","first-page":"386","article-title":"Improving word sense disambiguation by pseudo-samples","author":"Wang","year":"2004"},{"key":"10.1016\/j.datak.2025.102537_b19","series-title":"NLP2023 Workshop on Japanese Language Resources (JLR2023) of the 29th Annual Meeting of the Association for Natural Language Processing","article-title":"Nihon keizai shimbun article open corpus: Newspaper article corpus and morphological and syntactic information annotation. [nihon keizai shimbun kiji opun kopasu: Shimbunkiji kopasu to keitai \u22c5 togo joho anoteshon]","author":"Asahara","year":"2023"},{"key":"10.1016\/j.datak.2025.102537_b20","series-title":"Natural Language Processing and Information Systems","first-page":"93","article-title":"All-words pronunciation estimation of Japanese homographs using automatically tagged data","author":"Kobayashi","year":"2024"}],"container-title":["Data & Knowledge Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0169023X25001326?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0169023X25001326?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T05:32:14Z","timestamp":1773898334000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0169023X25001326"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":20,"alternative-id":["S0169023X25001326"],"URL":"https:\/\/doi.org\/10.1016\/j.datak.2025.102537","relation":{},"ISSN":["0169-023X"],"issn-type":[{"value":"0169-023X","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"All-words pronunciation estimation of Japanese homographs","name":"articletitle","label":"Article Title"},{"value":"Data & Knowledge Engineering","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.datak.2025.102537","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"102537"}}