{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T21:56:40Z","timestamp":1766267800830,"version":"3.37.3"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,12,2]],"date-time":"2022-12-02T00:00:00Z","timestamp":1669939200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,12,2]],"date-time":"2022-12-02T00:00:00Z","timestamp":1669939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"the Science and Technology Project of Hebei Education Department under Grant","award":["Nos.QN2021145"],"award-info":[{"award-number":["Nos.QN2021145"]}]},{"DOI":"10.13039\/501100019595","name":"Youth and Middle-aged Scientific and Technological Innovation Leading Talents Program of the Corps","doi-asserted-by":"publisher","award":["No.204200510002"],"award-info":[{"award-number":["No.204200510002"]}],"id":[{"id":"10.13039\/501100019595","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Hum-Cent Intell Syst"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Few-shot relation extraction is one of the current research focuses. The key to this research is to fully extract the relation semantic information through very little training data. Intuitively, raising the relation semantics awareness in sentences can improve the efficiency of the model to extract relation features to alleviate the overfitting problem in few-shot learning. Therefore, we propose an enhanced relation semantic feature model based on prototype network to extract relations from few-shot texts. Firstly, we design a multi-level embedding encoder with position information and Transformer, which uses local information in the text to enhance the relation semantics representation. Secondly, the encoded relation features are fed into the novel prototype network, which designs a method that utilizes query prototype-level attention to guide the extraction of supporting prototypes, thereby enhancing the prototypes representation to better classify the relations in query sentences. Finally, through experimental comparison and discussion, we prove and analyze the effectiveness of the proposed multi-level embedding encoder, and prototype-level attention can enhance the stability of the model. Furthermore, our model has substantial improvements over baseline methods.<\/jats:p>","DOI":"10.1007\/s44230-022-00012-0","type":"journal-article","created":{"date-parts":[[2022,12,2]],"date-time":"2022-12-02T09:08:23Z","timestamp":1669972103000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["A Prototype Network Enhanced Relation Semantic Representation for Few-shot Relation Extraction"],"prefix":"10.1007","volume":"3","author":[{"given":"Haitao","family":"He","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1607-3776","authenticated-orcid":false,"given":"Haoran","family":"Niu","sequence":"additional","affiliation":[]},{"given":"Jianzhou","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Qian","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Qikai","family":"Wei","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,12,2]]},"reference":[{"key":"12_CR1","doi-asserted-by":"publisher","first-page":"1215","DOI":"10.1007\/s12559-021-09917-7","volume":"13","author":"T Nayak","year":"2021","unstructured":"Nayak T, Majumder N, Goyal P, Poria S. Deep neural approaches to relation triplets extraction: a comprehensive survey. Cogn Comput. 2021;13:1215\u201332.","journal-title":"Cogn Comput"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Mintz M, Bills S, Snow R, Jurafsky D. Distant supervision for relation extraction without labeled data. Singapore. 2009.","DOI":"10.3115\/1690219.1690287"},{"key":"12_CR3","unstructured":"Bram S, Gilles V, Michael W. Ink: knowledge graph embeddings for node classification. Data Min Knowl Discov. 2022;48."},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Yang Z, Wang L, Ma B, Yang Y, Dong R, Wang Z. Rtjtn: relational triplet joint tagging network for joint entity and relation extraction. Comput Intell Neurosci. 2021.","DOI":"10.1155\/2021\/3447473"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Legrand J, Toussaint Y, Ra\u00efssi C, Coulet A. Syntax-based transfer learning for the task of biomedical relation extraction. J Biomed Semant. 2021.","DOI":"10.1186\/s13326-021-00248-y"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Yi Q, Zhang G, Zhang S. Utilizing entity-based gated convolution and multilevel sentence attention to improve distantly supervised relation extraction. Comput Intell Neurosci. 2021.","DOI":"10.1155\/2021\/6110885"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Wang Y, Bao J, Liu G, Wu Y, He X, Zhou B, Zhao T. Learning to decouple relations: few-shot relation classification with entity-guided attention and confusion-aware training. Coling. 2020.","DOI":"10.18653\/v1\/2020.coling-main.510"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Song S, Sun Y, Di Q. Multiple order semantic relation extraction. Neural Comput Appl. 2019;4563\u201376.","DOI":"10.1007\/s00521-018-3453-x"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Wang D, Tiwari P, Garg S, Zhu H, Bruza PD. Structural block driven enhanced convolutional neural representation for relation extraction. Appl Soft Comput. 2020;1568\u20134946.","DOI":"10.1016\/j.asoc.2019.105913"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Shao Y, Li H, Gu J, Qian L, Zhou G. Extraction of causal relations based on sbel and bert model. Database. 2021.","DOI":"10.1093\/database\/baab005"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Qiu Q, Xie Z, Ma K, Chen Z, Tao L. Spatially oriented convolutional neural network for spatial relation extraction from natural language texts. Transactions in GIS. 2021.","DOI":"10.1111\/tgis.12887"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Stanley O, Nazife D, Arif A. Chemical disease relation extraction task using genetic algorithm with two novel voting methods for classifier subset selection. Turk J Electr Eng Comput Sci. 2020;1179\u201396.","DOI":"10.3906\/elk-1906-46"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Woohwan J, Kyuseok S. T-rex: a topic-aware relation extraction model. Assoc Comput Mach. 2020;2073\u20136.","DOI":"10.1145\/3340531.3412133"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Abu-Salih B, Al-Tawil M, Aljarah I, Faris H, Wongthongtham P. Relational learning analysis of social politics using knowledge graph embedding. Data Min Knowl Discov. 2021.","DOI":"10.1007\/s10618-021-00760-w"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Fan S, Zhang B, Zhou S, Wang M, Li K. Few-shot relation extraction towards special interests. Big Data Res. 2021;2214\u20135796.","DOI":"10.1016\/j.bdr.2021.100273"},{"key":"12_CR16","unstructured":"Vinyals O, Blundell C, Lillicrap T, Wierstra D. Matching networks for one-shot learning. Adv Neural Inform Process Syst. 2016."},{"key":"12_CR17","unstructured":"Qu M, Gao T, Xhonneux L-P, Tang J. Few-shot relation extraction via bayesian meta-learning on relation graphs. ICML. 2020."},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Hui B, Liu L, Chen J, Zhou X, Nian Y. Few-shot relation classification by context attention-based prototypical networks with bert. EURASIP J Wirel Commun Netw. 2020.","DOI":"10.1186\/s13638-020-01720-6"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Deng S, Zhang N, Kang J, Zhang Y, Zhang W, Chen H. Meta-learning with dynamic-memory-based prototypical network for few-shot event detection. Assoc Comput Mach. 2020;151\u20139.","DOI":"10.1145\/3336191.3371796"},{"key":"12_CR20","unstructured":"Fangchao L, Xinyan X, Lingyong Y, Hongyu L, Xianpei H, Dai D, Hua W, Le S. From learning-to-match to learning-to-discriminate: global prototype learning for few-shot relation classification. Chin Comput Linguist. 2021."},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Lin Y, Shen S, Liu Z, Luan H, Sun M. Neural relation extraction with selective attention over instances. 2016;2124\u201333.","DOI":"10.18653\/v1\/P16-1200"},{"key":"12_CR22","unstructured":"Shanchan W, Yifan H. Enriching pre-trained language model with entity information for relation classification. 2019."},{"key":"12_CR23","unstructured":"Adam S, Sergey B, Matthew B, Daan W, Timothy L. One-shot learning with memory-augmented neural networks. In: 33nd international conference on machine learning. 2016."},{"key":"12_CR24","unstructured":"Gregory K, Zemel R, Salakhutdinov R. Siamese neural networks for one-shot image recognition. 2015;2."},{"key":"12_CR25","unstructured":"Chelsea F, Abbeel P, Levine S. Model-agnostic meta-learning for fast adaptation of deep networks. 2017."},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Han X, Zhu H, Yu P, Wang Z, Yao Y, Liu Z, Sun M. Fewrel: a large-scale supervised few-shot relation classification dataset with state-of-the-art evaluation. EMNLP. 2018.","DOI":"10.18653\/v1\/D18-1514"},{"key":"12_CR27","unstructured":"Jake S, Swersky K, Zemel R. Prototypical networks for few-shot learning. Adv Neural Inform Process Syst. 2017."},{"key":"12_CR28","unstructured":"Livio BS, Nicholas F, Jeffrey L, Tom K. Matching the blanks: distributional similarity for relation learning. ACL. 2019."},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Ye Z, Ling Z. Multi-level matching and aggregation network for few-shot relation classification. ACL. 2019.","DOI":"10.18653\/v1\/P19-1277"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Gao T, Han X, Liu Z, Sun M. Hybrid attention-based prototypical networks for noisy few-shot relation classification. 2019;6407\u201314.","DOI":"10.1609\/aaai.v33i01.33016407"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Wang K, Liew JH, Zou Y, Zhou D, Feng J. Panet: few-shot image semantic segmentation with prototype alignment. IEEE; 2019.","DOI":"10.1109\/ICCV.2019.00929"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Gao T, Han X, Zhu H, Liu Z, Li P, Sun M, Zhou J. Fewrel 2.0: towards more challenging few-shot relation classification. EMNLP. 2019;2124\u201333.","DOI":"10.18653\/v1\/D19-1649"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Fan M, Bai Y, Sun M, Li P, Bai Y, Sun M, Li P. Large margin prototypical network for few-shot relation classification with fine-grained features. Assoc Comput Machin. 2019;2353\u20136.","DOI":"10.1145\/3357384.3358100"},{"key":"12_CR34","doi-asserted-by":"crossref","unstructured":"Wen W, Liu Y, Ouyang C, Lin Q, Chung T. Enhanced prototypical network for few-shot relation extraction-sciencedirect. Inform Process Manage. 2021.","DOI":"10.1016\/j.ipm.2021.102596"},{"key":"12_CR35","unstructured":"Xiao Y, Jin Y, Hao K. Adaptive prototypical networks with label words and joint representation learning for few-shot relation classification. CoRR. 2021."},{"key":"12_CR36","doi-asserted-by":"publisher","first-page":"36995","DOI":"10.1109\/ACCESS.2022.3164688","volume":"10","author":"Z Li","year":"2022","unstructured":"Li Z, Ouyang F, Zhou C, He Y, Shen L. Few-shot relation classification research based on prototypical network and causal intervention. IEEE Access. 2022;10:36995\u20137002.","journal-title":"IEEE Access"}],"container-title":["Human-Centric Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44230-022-00012-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44230-022-00012-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44230-022-00012-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T20:43:47Z","timestamp":1728506627000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44230-022-00012-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,2]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,3]]}},"alternative-id":["12"],"URL":"https:\/\/doi.org\/10.1007\/s44230-022-00012-0","relation":{},"ISSN":["2667-1336"],"issn-type":[{"type":"electronic","value":"2667-1336"}],"subject":[],"published":{"date-parts":[[2022,12,2]]},"assertion":[{"value":"25 August 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 November 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 December 2022","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 they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The authors hereby consent to publication of the work.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"This article does not contain any studies with animals performed by any of the authors.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval and consent to participate"}}]}}