{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T07:05:57Z","timestamp":1777705557177,"version":"3.51.4"},"reference-count":43,"publisher":"SAGE Publications","issue":"4","license":[{"start":{"date-parts":[[2024,3,29]],"date-time":"2024-03-29T00:00:00Z","timestamp":1711670400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"published-print":{"date-parts":[[2025,2,28]]},"abstract":"<jats:p>The short text matching models can be roughly divided into representation-based and interaction-based approaches. However, current representation-based text matching models often lack the ability to handle sentence pairs and typically only perform feature interactions at the network\u2019s top layer, which can lead to a loss of semantic focus. The interactive text matching model has significant shortcomings in extracting differential information between sentences and may ignore global information. To address these issues, this article proposes a model structure that combines a dual-tower architecture with an interactive component, which compensates for their respective weaknesses in extracting sentence semantic information. Simultaneously, a method for integrating semantic information is proposed, enabling the model to capture both the interactive information between sentence pairs and the differential information between sentences, thereby addressing the issues with the aforementioned approaches. In the process of network training, a combination of cross-entropy and cosine similarity is used to calculate the model loss. The model is optimized to a stable state. Experiments on the commonly used datasets of QQP and MRPC validate the effectiveness of the proposed model, and its performance is stably improved.<\/jats:p>","DOI":"10.3233\/jifs-230268","type":"journal-article","created":{"date-parts":[[2024,3,29]],"date-time":"2024-03-29T12:39:45Z","timestamp":1711715985000},"page":"477-489","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["IMAI: A short text matching model integrating multi-angle information"],"prefix":"10.1177","volume":"48","author":[{"given":"Binghui","family":"Luo","sequence":"first","affiliation":[{"name":"School of Computer Science &amp; School of Cyberspace Science, Xiangtan University, Hunan Province, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science &amp; School of Cyberspace Science, Xiangtan University, Hunan Province, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Long","family":"Qin","sequence":"additional","affiliation":[{"name":"School of Computer Science &amp; School of Cyberspace Science, Xiangtan University, Hunan Province, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolong","family":"Jiao","sequence":"additional","affiliation":[{"name":"School of Computer Science &amp; School of Cyberspace Science, Xiangtan University, Hunan Province, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wengui","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science &amp; School of Cyberspace Science, Xiangtan University, Hunan Province, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2024,3,29]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3527546.3527552"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-021-02348-9"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17616"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eij.2018.11.001"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.104"},{"key":"e_1_3_1_7_2","unstructured":"JalilifardA. Carid\u00c3V.F. MansanoA. CristoR.Semantic sensitive TF-IDF to determine word relevance in documents CoRR abs\/2001.09896 (2020)."},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.5765"},{"key":"e_1_3_1_9_2","doi-asserted-by":"crossref","unstructured":"TrotmanA. PuurulaA. BurgessB. Improvements to BM25 and Language Models Examined in: Proceedings of the 2014 Australasian Document Computing Symposium on- ADCS \u201914 ACM Press Melbourne VIC Australia 2014 pp. 58\u201365. URL: https:\/\/doi.org\/10.1145\/2682862.2682863.","DOI":"10.1145\/2682862.2682863"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIS50930.2021.9395976"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.3906\/elk-1912-62"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.psychres.2021.114135"},{"key":"e_1_3_1_13_2","unstructured":"RadfordA. NarasimhanK. SalimansT. SutskeverI. et al. Improving language understanding by generative pre-training (2018)."},{"key":"e_1_3_1_14_2","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding in:","author":"Kenton J.D.M.-W.C.","year":"2019","unstructured":"KentonJ.D.M.-W.C. and ToutanovaL.K., Bert: Pre-training of deep bidirectional transformers for language understanding in:, Proceedings of naacL-HLT (2019), 4171\u20134186.","journal-title":"Proceedings of naacL-HLT"},{"key":"e_1_3_1_15_2","first-page":"5754","article-title":"Xlnet: Generalized autoregressive pretraining for language understanding in:","author":"Yang Z.","year":"2019","unstructured":"YangZ., DaiZ., YangY., CarbonellJ.G., SalakhutdinovR. and LeQ.V., Xlnet: Generalized autoregressive pretraining for language understanding in:, NeurIPS (2019), 5754\u20135764.","journal-title":"NeurIPS"},{"key":"e_1_3_1_16_2","unstructured":"LiuY. OttM. GoyalN. DuJ. JoshiM. ChenD. LevyO. LewisM. ZettlemoyerL. StoyanovV. Roberta:A robustly optimized bert pretraining approach arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_1_17_2","unstructured":"SuJ. LuY. PanS. WenB. LiuY. Roformer: Enhanced transformer with rotary position embedding arXiv preprint arXiv:2104.09864 (2021)."},{"key":"e_1_3_1_18_2","unstructured":"IyerS. DandekarN. CsernaiK. et al. First quora dataset release: Question pairs. data. quora. com (2017)."},{"key":"e_1_3_1_19_2","unstructured":"DolanB. BrockettC. Automatically constructing a corpus of sentential paraphrases in: Third International Workshop on Paraphrasing (IWP2005) 2005."},{"key":"e_1_3_1_20_2","article-title":"Deconvolutional paragraph representation learning,","volume":"30","author":"Zhang Y.","year":"2017","unstructured":"ZhangY., ShenD., WangG., GanZ., HenaoR. and CarinL., Deconvolutional paragraph representation learning, , Advances in Neural Information Processing Systems 30 (2017).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11991"},{"key":"e_1_3_1_22_2","unstructured":"YogatamaD. DyerC. LingW. BlunsomP. Generative and discriminative text classification with recurrent neural networks arXiv preprint arXiv:1703.01898 (2017)."},{"key":"e_1_3_1_23_2","first-page":"356","article-title":"Topic compositional neural language model in:","author":"Wang W.","year":"2018","unstructured":"WangW., GanZ., WangW., ShenD., HuangJ., PingW., SatheeshS. and CarinL., Topic compositional neural language model in:, International Conference on Artificial Intelligence and Statistics (2018), 356\u2013365.","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-020-9159-0"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1174"},{"key":"e_1_3_1_26_2","unstructured":"LinZ. FengM. SantosC.N.d. YuM. XiangB. ZhouB. BengioY. A structured self-attentive sentence embedding arXiv preprint arXiv:1703.03130 (2017)."},{"key":"e_1_3_1_27_2","article-title":"Attention is all you need,","volume":"30","author":"Vaswani A.","year":"2017","unstructured":"VaswaniA., ShazeerN., ParmarN., UszkoreitJ., JonesL., GomezA.N., Kaiser\u0141. and PolosukhinI., Attention is all you need, , {Advances in Neural Information Processing Systems 30 (2017).","journal-title":"{Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_28_2","unstructured":"LanZ. ChenM. GoodmanS. GimpelK. SharmaP. SoricutR. Albert: A lite bert for self-supervised learning of language representations arXiv preprint arXiv:1909.11942 (2019)."},{"key":"e_1_3_1_29_2","unstructured":"HeP. LiuX. GaoJ. ChenW. Deberta: Decodingenhanced bert with disentangled attention arXiv preprint arXiv:2006.03654 (2020)."},{"key":"e_1_3_1_30_2","first-page":"2333","article-title":"Learning deep structured semantic models for web search using clickthrough data in:","author":"Huang P.-S.","year":"2013","unstructured":"HuangP.-S., HeX., GaoJ., DengL., AceroA. and HeckL., Learning deep structured semantic models for web search using clickthrough data in:, Proceedings of the 22nd ACM international conference on Information & Knowledge Management (2013), 2333\u20132338.","journal-title":"Proceedings of the 22nd ACM international conference on Information & Knowledge Management"},{"key":"e_1_3_1_31_2","doi-asserted-by":"crossref","unstructured":"ReimersN. GurevychI. Sentence-bert: Sentence embeddings using siamese bert-networks arXiv preprint arXiv:1908.10084 (2019).","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_1_32_2","doi-asserted-by":"crossref","unstructured":"YanY. LiR. WangS. ZhangF. WuW. XuW. Consert: Acontrastive framework for self-supervised sentence representation transfer arXiv preprint arXiv:2105.11741 (2021).","DOI":"10.18653\/v1\/2021.acl-long.393"},{"key":"e_1_3_1_33_2","doi-asserted-by":"crossref","unstructured":"GaoT. YaoX. ChenD. Simcse: Simple contrastive learning of sentence embeddings arXiv preprint arXiv:2104.08821 (2021).","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"e_1_3_1_34_2","unstructured":"ChenQ. ZhuX. LingZ. WeiS. JiangH. InkpenD. Enhanced lstm for natural language inference arXiv preprint arXiv:1609.06038 (2016)."},{"key":"e_1_3_1_35_2","doi-asserted-by":"crossref","unstructured":"YangR. ZhangJ. GaoX. JiF. ChenH. Simple and effective text matching with richer alignment features arXiv preprint arXiv:1908.00300 (2019).","DOI":"10.18653\/v1\/P19-1465"},{"key":"e_1_3_1_36_2","first-page":"1829","article-title":"Dc-bert: Decoupling question and document for efficient contextual encoding in:","author":"Nie P.","year":"2020","unstructured":"NieP., ZhangY., GengX., RamamurthyA., SongL. and JiangD., Dc-bert: Decoupling question and document for efficient contextual encoding in:, Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval (2020), 1829\u20131832.","journal-title":"Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval"},{"key":"e_1_3_1_37_2","unstructured":"XuS. PangL. ShenH. ChengX. Improving multi-task generalization ability for neural text matching via prompt learning arXiv preprint arXiv:2204.02725 (2022)."},{"key":"e_1_3_1_38_2","doi-asserted-by":"crossref","unstructured":"ZouY. LiuH. GuiT. WangJ. ZhangQ. TangM. LiH. WangD. Divide and conquer: Text semantic matching with disentangled keywords and intents arXiv preprint arXiv:2203.02898 (2022).","DOI":"10.18653\/v1\/2022.findings-acl.287"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.152"},{"key":"e_1_3_1_40_2","doi-asserted-by":"crossref","unstructured":"WangA. SinghA. MichaelJ. HillF. LevyO. BowmanS.R. Bowman Glue: A multi-task benchmark and analysis platform for natural language understanding arXiv preprint arXiv:1804.07461 (2018).","DOI":"10.18653\/v1\/W18-5446"},{"key":"e_1_3_1_41_2","doi-asserted-by":"crossref","unstructured":"ZhangK. WuL. LvG. WangM. ChenE. RuanS. Making the relation matters: Relation of relation learning network for sentence semantic matching in: Proceedings of the AAAI Conference on Artificial Intelligence volume 35 2021 pp. 14411\u201314419.","DOI":"10.1609\/aaai.v35i16.17694"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-demo.41"},{"key":"e_1_3_1_43_2","unstructured":"WolfT. DebutL. SanhV. ChaumondJ. DelangueC. MoiA. CistacP. RaultT. LoufR. FuntowiczM. et al. Huggingface\u2019s transformers: State-of-the-art natural language processing arXiv preprint arXiv:1910.03771 (2019)."},{"key":"e_1_3_1_44_2","unstructured":"LoshchilovI. HutterF. Fixing weight decay regularization in adam (2018)."}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-230268","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/JIFS-230268","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-230268","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:44:13Z","timestamp":1777455853000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.3233\/JIFS-230268"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,29]]},"references-count":43,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,2,28]]}},"alternative-id":["10.3233\/JIFS-230268"],"URL":"https:\/\/doi.org\/10.3233\/jifs-230268","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,29]]}}}