{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T10:55:24Z","timestamp":1773658524392,"version":"3.50.1"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"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":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s13042-025-02888-3","type":"journal-article","created":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T06:19:36Z","timestamp":1770013176000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-source knowledge enhancement for multimodal semantic representation"],"prefix":"10.1007","volume":"17","author":[{"given":"Pei-Yuan","family":"Lai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing-Yun","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"De-Zhang","family":"Liao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huan-Tao","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Man-Sheng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chang-Dong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,2]]},"reference":[{"issue":"10","key":"2888_CR1","doi-asserted-by":"publisher","first-page":"2943","DOI":"10.1007\/s13042-022-01574-y","volume":"13","author":"B Wang","year":"2022","unstructured":"Wang B, Sun Y, Chu Y, Yang Z, Lin H (2022) Global-locality preserving projection for word embedding. Int J Mach Learn Cybern 13(10):2943\u20132956","journal-title":"Int J Mach Learn Cybern"},{"key":"2888_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neucom.2020.03.093","volume":"406","author":"Z Zhan","year":"2020","unstructured":"Zhan Z, Hou Z, Yang Q, Zhao J, Zhang Y, Hu C (2020) Knowledge attention sandwich neural network for text classification. Neurocomputing 406:1\u201311","journal-title":"Neurocomputing"},{"issue":"8","key":"2888_CR3","doi-asserted-by":"publisher","first-page":"3127","DOI":"10.1007\/s13042-023-02084-1","volume":"15","author":"W Wang","year":"2024","unstructured":"Wang W, Chen J, Zhang X, Xie B (2024) Combining core points and cluster-level semantic similarity for self-supervised clustering. Int J Mach Learn Cybern 15(8):3127\u20133142","journal-title":"Int J Mach Learn Cybern"},{"key":"2888_CR4","doi-asserted-by":"crossref","unstructured":"Wieting J, Berg-Kirkpatrick T, Gimpel K, Neubig G (2019) Beyond BLEU: training neural machine translation with semantic similarity. In: ACL, pp. 4344\u20134355","DOI":"10.18653\/v1\/P19-1427"},{"issue":"4","key":"2888_CR5","doi-asserted-by":"publisher","first-page":"2973","DOI":"10.1109\/TCSVT.2023.3307554","volume":"34","author":"K Zhang","year":"2024","unstructured":"Zhang K, Hu B, Zhang H, Li Z, Mao Z (2024) Enhanced semantic similarity learning framework for image-text matching. IEEE Trans Circuits Syst Video Technol 34(4):2973\u20132988","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"2888_CR6","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/j.neucom.2020.04.084","volume":"403","author":"F Liu","year":"2020","unstructured":"Liu F, Zheng L, Zheng J (2020) Hienn-dwe: A hierarchical neural network with dynamic word embeddings for document level sentiment classification. Neurocomputing 403:21\u201332","journal-title":"Neurocomputing"},{"issue":"3","key":"2888_CR7","doi-asserted-by":"publisher","first-page":"4139","DOI":"10.1109\/TCSS.2024.3360378","volume":"11","author":"T Suresh","year":"2024","unstructured":"Suresh T, Sengupta A, Akhtar MS, Chakraborty T (2024) A comprehensive understanding of code-mixed language semantics using hierarchical transformer. IEEE Trans Comput Soc Syst 11(3):4139\u20134148","journal-title":"IEEE Trans Comput Soc Syst"},{"issue":"29","key":"2888_CR8","doi-asserted-by":"publisher","first-page":"42805","DOI":"10.1007\/s11042-022-13488-6","volume":"81","author":"FL Wang","year":"2022","unstructured":"Wang FL, Lu Y, Cheng G, Xie H, Rao Y (2022) Learning chinese word embeddings from semantic and phonetic components. Multim Tools Appl 81(29):42805\u201342820","journal-title":"Multim Tools Appl"},{"key":"2888_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128667","volume":"611","author":"S Hou","year":"2025","unstructured":"Hou S, Qian Y, Chen J, Zhao J, Lv H, Zhang J, Leng H, Ma M (2025) Hiner: Hierarchical feature fusion for chinese named entity recognition. Neurocomputing 611:128667","journal-title":"Neurocomputing"},{"key":"2888_CR10","doi-asserted-by":"crossref","unstructured":"Hou S, Qian Y, Chen J, Zhao J, Lv H, Lu Y, Leng H (2024) Hierarchical mutual prompt for chinese few-shot event detection. In: ICIC (LNAI), vol. 14878, pp. 389\u2013397","DOI":"10.1007\/978-981-97-5672-8_33"},{"key":"2888_CR11","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1613\/jair.2308","volume":"30","author":"SP Ponzetto","year":"2007","unstructured":"Ponzetto SP, Strube M (2007) Knowledge derived from wikipedia for computing semantic relatedness. J Artif Intell Res 30:181\u2013212","journal-title":"J Artif Intell Res"},{"key":"2888_CR12","doi-asserted-by":"crossref","unstructured":"Hou S, Qian Y, Chen J, Zhao J, Leng H (2024) MBA-NER: multi-granularity entity boundary-aware contrastive enhanced for two-stage few-shot named entity recognition. In: PRCV, vol. 15032, pp. 17\u201330","DOI":"10.1007\/978-981-97-8490-5_2"},{"key":"2888_CR13","unstructured":"Devlin J, Chang M, Lee K, Toutanova K (2024) BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT, pp. 4171\u20134186x"},{"key":"2888_CR14","doi-asserted-by":"crossref","unstructured":"Duan X, Tan D, Fang L, Zhou Y, He C, Chen Z, Wu L, Chen G, Gong Z, Luo W, Guan Q (2024) Reason-and-execute prompting: Enhancing multi-modal large language models for solving geometry questions. In: ACM MM, pp. 6959\u20136968","DOI":"10.1145\/3664647.3681484"},{"key":"2888_CR15","doi-asserted-by":"crossref","unstructured":"Hong Z, Yuan Z, Chen H, Zhang Q, Huang F, Huang X (2024) Knowledge-to-SQL: Enhancing SQL generation with data expert LLM. CoRR arXiv:2402.11517","DOI":"10.18653\/v1\/2024.findings-acl.653"},{"issue":"5","key":"2888_CR16","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1145\/3653712","volume":"42","author":"Y Tang","year":"2024","unstructured":"Tang Y, Zhang R, Guo J, Rijke M, Chen W, Cheng X (2024) Listwise generative retrieval models via a sequential learning process. ACM Trans Inf Syst 42(5):133\u2013113331","journal-title":"ACM Trans Inf Syst"},{"issue":"3","key":"2888_CR17","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1007\/s41019-021-00162-4","volume":"6","author":"M Zhu","year":"2021","unstructured":"Zhu M, Shen D, Xu L, Wang X (2021) Scalable multi-grained cross-modal similarity query with interpretability. Data Sci Eng 6(3):280\u2013293","journal-title":"Data Sci Eng"},{"issue":"10","key":"2888_CR18","doi-asserted-by":"publisher","first-page":"4423","DOI":"10.1007\/s13042-024-02154-y","volume":"15","author":"S Xiong","year":"2024","unstructured":"Xiong S, Pan L, Ma X, Hu Q, Beckman E (2024) Unsupervised deep hashing with multiple similarity preservation for cross-modal image-text retrieval. Int J Mach Learn Cybern 15(10):4423\u20134434","journal-title":"Int J Mach Learn Cybern"},{"key":"2888_CR19","doi-asserted-by":"crossref","unstructured":"Nian F, Bao B, Li T, Xu C (2017) Multi-modal knowledge representation learning via webly-supervised relationships mining. In: ACMMM, pp. 411\u2013419","DOI":"10.1145\/3123266.3123443"},{"key":"2888_CR20","doi-asserted-by":"crossref","unstructured":"Wang Y, Qian S, Hu J, Fang Q, Xu C (2020) Fake news detection via knowledge-driven multimodal graph convolutional networks. In: ICMR, pp. 540\u2013547","DOI":"10.1145\/3372278.3390713"},{"key":"2888_CR21","doi-asserted-by":"publisher","first-page":"1131","DOI":"10.1613\/jair.1.12918","volume":"73","author":"E Erdem","year":"2022","unstructured":"Erdem E, Kuyu M, Yagcioglu S, Frank A, Parcalabescu L, Plank B, Babii A, Turuta O, Erdem A, Calixto I, Lloret E, Apostol ES, Truica C, Sandrih B, Martincic-Ipsic S, Berend G, Gatt A, Korvel G (2022) Neural natural language generation: A survey on multilinguality, multimodality, controllability and learning. J Artif Intell Res 73:1131\u20131207","journal-title":"J Artif Intell Res"},{"key":"2888_CR22","doi-asserted-by":"crossref","unstructured":"Zhang M, Mosbach M, Adelani DI, Hedderich MA, Klakow D (2022) MCSE: multimodal contrastive learning of sentence embeddings. In: NAACL, pp. 5959\u20135969","DOI":"10.18653\/v1\/2022.naacl-main.436"},{"key":"2888_CR23","doi-asserted-by":"publisher","first-page":"3592","DOI":"10.1109\/TASLP.2021.3129331","volume":"29","author":"B Chen","year":"2021","unstructured":"Chen B, Cao Q, Hou M, Zhang Z, Lu G, Zhang D (2021) Multimodal emotion recognition with temporal and semantic consistency. IEEE ACM Trans Audio Speech Lang Process 29:3592\u20133603","journal-title":"IEEE ACM Trans Audio Speech Lang Process"},{"key":"2888_CR24","doi-asserted-by":"crossref","unstructured":"Guo J, Tang J, Dai W, Ding Y, Kong W (2022) Dynamically adjust word representations using unaligned multimodal information. In: MM ACM, pp. 3394\u20133402","DOI":"10.1145\/3503161.3548137"},{"key":"2888_CR25","doi-asserted-by":"crossref","unstructured":"Chen B, Rouditchenko A, Duarte K, Kuehne H, Thomas S, Boggust AW, Panda R, Kingsbury B, Feris R, Harwath D, Glass JR, Picheny M, Chang S (2021) Multimodal clustering networks for self-supervised learning from unlabeled videos. In: ICCV, pp. 7992\u20138001","DOI":"10.1109\/ICCV48922.2021.00791"},{"key":"2888_CR26","doi-asserted-by":"crossref","unstructured":"Chen Z, Huang X, Guan Q, Lin L, Luo W (2023) A retrospect to multi-prompt learning across vision and language. In: IEEE\/CVF ICCV, pp. 22133\u201322144","DOI":"10.1109\/ICCV51070.2023.02028"},{"issue":"5","key":"2888_CR27","first-page":"162","volume":"19","author":"D Feng","year":"2023","unstructured":"Feng D, He X, Peng Y (2023) MKVSE: multimodal knowledge enhanced visual-semantic embedding for image-text retrieval. ACM Trans Multim Comput Commun Appl 19(5):162\u2013116221","journal-title":"ACM Trans Multim Comput Commun Appl"},{"key":"2888_CR28","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1613\/jair.1.12078","volume":"70","author":"Y Yin","year":"2021","unstructured":"Yin Y, Lai S, Song L, Zhou C, Han X, Yao J, Su J (2021) An external knowledge enhanced graph-based neural network for sentence ordering. J Artif Intell Res 70:545\u2013566","journal-title":"J Artif Intell Res"},{"key":"2888_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.07.013","volume":"182","author":"HT Nguyen","year":"2019","unstructured":"Nguyen HT, Duong PH, Cambria E (2019) Learning short-text semantic similarity with word embeddings and external knowledge sources. Knowl Based Syst 182:104842","journal-title":"Knowl Based Syst"},{"key":"2888_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109906","volume":"257","author":"Y Deng","year":"2022","unstructured":"Deng Y, Bai W, Jiang Y, Tang Y (2022) Subgraph-based feature fusion models for semantic similarity computation in heterogeneous knowledge graphs. Knowl Based Syst 257:109906","journal-title":"Knowl Based Syst"},{"key":"2888_CR31","doi-asserted-by":"crossref","unstructured":"Huang Y, Tang J, Chen Z, Zhang R, Zhang X, Chen W, Zhao Z, Zhao Z, Lv T, Hu Z, Zhang W (2024) Structure-clip: Towards scene graph knowledge to enhance multi-modal structured representations. In: AAAI, pp. 2417\u20132425","DOI":"10.1609\/aaai.v38i3.28017"},{"key":"2888_CR32","doi-asserted-by":"crossref","unstructured":"Liu W, Zhou P, Zhao Z, Wang Z, Ju Q, Deng H, Wang P (2020) K-BERT: enabling language representation with knowledge graph. In: AAAI, pp. 2901\u20132908","DOI":"10.1609\/aaai.v34i03.5681"},{"key":"2888_CR33","doi-asserted-by":"crossref","unstructured":"Xia T, Wang Y, Tian Y, Chang Y (2021) Using prior knowledge to guide bert\u2019s attention in semantic textual matching tasks. In: WWW, pp. 2466\u20132475","DOI":"10.1145\/3442381.3449988"},{"key":"2888_CR34","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126583","volume":"555","author":"Y Li","year":"2023","unstructured":"Li Y, Chen J, Li Y, Yu T, Chen X, Zheng H (2023) Embracing ambiguity: Improving similarity-oriented tasks with contextual synonym knowledge. Neurocomputing 555:126583","journal-title":"Neurocomputing"},{"key":"2888_CR35","unstructured":"Sun Y, Wang S, Feng S, Ding S, Pang C, Shang J, Liu J, Chen X, Zhao Y, Lu Y, Liu W, Wu Z, Gong W, Liang J, Shang Z, Sun P, Liu W, Ouyang X, Yu D, Tian H, Wu H, Wang H (2021) ERNIE 3.0: Large-scale knowledge enhanced pre-training for language understanding and generation. CoRR arXiv:2107.02137"},{"key":"2888_CR36","unstructured":"Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Levy O, Lewis M, Zettlemoyer L, Stoyanov V (2019) Roberta: A robustly optimized BERT pretraining approach. CoRR arXiv:1907.11692"},{"key":"2888_CR37","unstructured":"Chen X, Xu L, Liu Z, Sun M, Luan H (2015) Joint learning of character and word embeddings. In: Yang Q, Wooldridge MJ (eds) IJCAI, pp. 1236\u20131242"},{"issue":"1","key":"2888_CR38","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1145\/503104.503110","volume":"20","author":"L Finkelstein","year":"2002","unstructured":"Finkelstein L, Gabrilovich E, Matias Y, Rivlin E, Solan Z, Wolfman G, Ruppin E (2002) Placing search in context: the concept revisited. ACM Trans Inf Syst 20(1):116\u2013131","journal-title":"ACM Trans Inf Syst"},{"issue":"10","key":"2888_CR39","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1145\/365628.365657","volume":"8","author":"H Rubenstein","year":"1965","unstructured":"Rubenstein H, Goodenough JB (1965) Contextual correlates of synonymy. Commun ACM 8(10):627\u2013633","journal-title":"Commun ACM"},{"issue":"1","key":"2888_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/01690969108406936","volume":"6","author":"GA Miller","year":"1991","unstructured":"Miller GA, Charles WG (1991) Contextual correlates of semantic similarity. Lang Cognit Process 6(1):1\u201328","journal-title":"Lang Cognit Process"},{"key":"2888_CR41","unstructured":"Mikolov T, Chen K, Corrado G, Dean J (2013) Efficient estimation of word representations in vector space. In: ICLR"},{"key":"2888_CR42","doi-asserted-by":"crossref","unstructured":"Su T, Lee H (2017) Learning chinese word representations from glyphs of characters. In: EMNLP, pp. 264\u2013273","DOI":"10.18653\/v1\/D17-1025"},{"key":"2888_CR43","doi-asserted-by":"crossref","unstructured":"Yu J, Jian X, Xin H, Song Y (2017) Joint embeddings of chinese words, characters, and fine-grained subcharacter components. In: EMNLP, pp. 286\u2013291","DOI":"10.18653\/v1\/D17-1027"},{"key":"2888_CR44","doi-asserted-by":"crossref","unstructured":"Sun C, Qiu X, Huang X (2019) VCWE: visual character-enhanced word embeddings. In: NAACL-HLT, pp. 2710\u20132719","DOI":"10.18653\/v1\/N19-1277"},{"key":"2888_CR45","doi-asserted-by":"crossref","unstructured":"Su H, Shi W, Shen X, Xiao Z, Ji T, Fang J, Zhou J (2022) Rocbert: Robust chinese bert with multimodal contrastive pretraining. In: ACL, pp. 921\u2013931","DOI":"10.18653\/v1\/2022.acl-long.65"},{"key":"2888_CR46","doi-asserted-by":"crossref","unstructured":"Sun Z, Li X, Sun X, Meng Y, Ao X, He Q, Wu F, Li J (2021) Chinesebert: Chinese pretraining enhanced by glyph and pinyin information. In: ACL\/IJCNLP, pp. 2065\u20132075","DOI":"10.18653\/v1\/2021.acl-long.161"},{"key":"2888_CR47","doi-asserted-by":"crossref","unstructured":"Cui Y, Che W, Liu T, Qin B, Wang S, Hu G (2020) Revisiting pre-trained models for chinese natural language processing. In: EMNLP, pp. 657\u2013668","DOI":"10.18653\/v1\/2020.findings-emnlp.58"},{"key":"2888_CR48","unstructured":"Lee C, Roy R, Xu M, Raiman J, Shoeybi M, Catanzaro B, Ping W (2024) Nv-embed: Improved techniques for training llms as generalist embedding models. arXiv preprint arXiv:2405.17428"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02888-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-025-02888-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02888-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T09:56:21Z","timestamp":1773654981000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-025-02888-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":48,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["2888"],"URL":"https:\/\/doi.org\/10.1007\/s13042-025-02888-3","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]},"assertion":[{"value":"12 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"68"}}