{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:30:55Z","timestamp":1778693455940,"version":"3.51.4"},"reference-count":43,"publisher":"Wiley","license":[{"start":{"date-parts":[[2021,11,29]],"date-time":"2021-11-29T00:00:00Z","timestamp":1638144000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Basic Research Program of China","doi-asserted-by":"publisher","award":["2017YFC0820700"],"award-info":[{"award-number":["2017YFC0820700"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Basic Research Program of China","doi-asserted-by":"publisher","award":["2020YFG0168"],"award-info":[{"award-number":["2020YFG0168"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key R&D Projects in Sichuan Province","award":["2017YFC0820700"],"award-info":[{"award-number":["2017YFC0820700"]}]},{"name":"Key R&D Projects in Sichuan Province","award":["2020YFG0168"],"award-info":[{"award-number":["2020YFG0168"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Scientific Programming"],"published-print":{"date-parts":[[2021,11,29]]},"abstract":"<jats:p>Aspect-level sentiment analysis identifies the sentiment polarity of aspect terms in complex sentences, which is useful in a wide range of applications. It is a highly challenging task and attracts the attention of many researchers in the natural language processing field. In order to obtain a better aspect representation, a wide range of existing methods design complex attention mechanisms to establish the connection between entity words and their context. With the limited size of data collections in aspect-level sentiment analysis, mainly because of the high annotation workload, the risk of overfitting is greatly increased. In this paper, we propose a Shared Multitask Learning Network (SMLN), which jointly trains auxiliary tasks that are highly related to aspect-level sentiment analysis. Specifically, we use opinion term extraction due to its high correlation with the main task. Through a custom-designed Cross Interaction Unit (CIU), effective information of the opinion term extraction task is passed to the main task, with performance improvement in both directions. Experimental results on SemEval-2014 and SemEval-2015 datasets demonstrate the competitive performance of SMLN in comparison to baseline methods.<\/jats:p>","DOI":"10.1155\/2021\/2055555","type":"journal-article","created":{"date-parts":[[2021,11,29]],"date-time":"2021-11-29T23:50:09Z","timestamp":1638229809000},"page":"1-9","source":"Crossref","is-referenced-by-count":7,"title":["Multitask Learning for Aspect-Based Sentiment Classification"],"prefix":"10.1155","volume":"2021","author":[{"given":"Chunhua","family":"Yao","sequence":"first","affiliation":[{"name":"The 30th Research Institute of China Electronics Technology Group Corporation, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9709-029X","authenticated-orcid":true,"given":"Xinyu","family":"Song","sequence":"additional","affiliation":[{"name":"Chengdu University of Information Technology, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7927-7181","authenticated-orcid":true,"given":"Xuelei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chengdu University of Information Technology, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7091-812X","authenticated-orcid":true,"given":"Weicheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Chengdu University of Information Technology, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6231-7810","authenticated-orcid":true,"given":"Ao","family":"Feng","sequence":"additional","affiliation":[{"name":"Chengdu University of Information Technology, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","reference":[{"key":"1","doi-asserted-by":"publisher","DOI":"10.1145\/1014052.1014073"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1561\/1500000011"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.2200\/s00416ed1v01y201204hlt016"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/s14-2004"},{"key":"5","first-page":"151","article-title":"Target-dependent twitter sentiment classification","author":"L. Jiang"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/p14-2009"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.5555\/2832415.2832437"},{"key":"8","article-title":"Effective lstms for target-dependent sentiment classification","author":"D. Tang","year":"2015"},{"key":"9","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-30490-4_9","article-title":"Attentional encoder network for targeted sentiment classification","author":"Y. Song","year":"2019"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/s14-2036"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/s14-2076"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1058"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018714"},{"key":"14","article-title":"Interactive attention networks for aspect-level sentiment classification","author":"D. Ma","year":"2017"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1380"},{"key":"16","article-title":"An overview of multi-task learning in deep neural networks","author":"S. Ruder","year":"2017"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1023\/a:1007379606734"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"19","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1092"},{"key":"20","article-title":"Recurrent neural network for text classification with multi-task learning","author":"P. Liu","year":"2016"},{"key":"21","article-title":"Exploiting document knowledge for aspect-level sentiment classification","author":"R. He","year":"2018"},{"key":"22","article-title":"An interactive multi-task learning network for end-to-end aspect-based sentiment analysis","author":"R. He","year":"2019"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1023"},{"key":"24","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D16-1021","article-title":"Aspect level sentiment classification with deep memory network","author":"D. Tang","year":"2016"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1047"},{"key":"26","first-page":"1077","article-title":"Enhanced aspect level sentiment classification with auxiliary memory","author":"P. Zhu"},{"key":"27","article-title":"Utilizing bert for aspect-based sentiment analysis via constructing auxiliary sentence","author":"C. Sun","year":"2019"},{"key":"28","article-title":"Bert post-training for review reading comprehension and aspect-based sentiment analysis","author":"H. Xu","year":"2019"},{"key":"29","doi-asserted-by":"publisher","DOI":"10.1109\/access.2019.2946594"},{"key":"30","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106292"},{"key":"31","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.106755"},{"key":"32","article-title":"Bert: pre-training of deep bidirectional transformers for language understanding","author":"J. Devlin","year":"2018"},{"key":"33","first-page":"5998","article-title":"Attention is all you need","author":"A. Vaswani","year":"2017"},{"key":"34","article-title":"Google\u2019s neural machine translation system: bridging the gap between human and machine translation","author":"Y. Wu","year":"2016"},{"key":"35","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298050"},{"key":"36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/s15-2082"},{"key":"37","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D16-1059","article-title":"Recursive neural conditional random fields for aspect-based sentiment analysis","author":"W. Wang","year":"2016"},{"key":"38","article-title":"Transformation networks for target-oriented sentiment classification","author":"X. Li","year":"2018"},{"key":"39","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00308"},{"key":"40","article-title":"Double embeddings and cnn-based sequence labeling for aspect extraction","author":"H. Xu","year":"2018"},{"key":"41","article-title":"Efficient estimation of word representations in vector space","author":"T. Mikolov","year":"2013"},{"key":"42","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1162"},{"key":"43","article-title":"Attention is not all you need: pure attention loses rank doubly exponentially with depth","author":"Y. Dong","year":"2021"}],"container-title":["Scientific Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/sp\/2021\/2055555.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/sp\/2021\/2055555.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/sp\/2021\/2055555.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,29]],"date-time":"2021-11-29T23:50:15Z","timestamp":1638229815000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/sp\/2021\/2055555\/"}},"subtitle":[],"editor":[{"given":"Sze-Teng","family":"Liong","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,11,29]]},"references-count":43,"alternative-id":["2055555","2055555"],"URL":"https:\/\/doi.org\/10.1155\/2021\/2055555","relation":{},"ISSN":["1875-919X","1058-9244"],"issn-type":[{"value":"1875-919X","type":"electronic"},{"value":"1058-9244","type":"print"}],"subject":[],"published":{"date-parts":[[2021,11,29]]}}}