{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T15:08:18Z","timestamp":1753888098779,"version":"3.41.2"},"reference-count":49,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,3,30]],"date-time":"2021-03-30T00:00:00Z","timestamp":1617062400000},"content-version":"vor","delay-in-days":88,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["Y835120378"],"award-info":[{"award-number":["Y835120378"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computational Intelligence and Neuroscience"],"published-print":{"date-parts":[[2021,1]]},"abstract":"<jats:p>Target\u2010oriented opinion words extraction (TOWE) seeks to identify opinion expressions oriented to a specific target, and it is a crucial step toward fine\u2010grained opinion mining. Recent neural networks have achieved significant success in this task by building target\u2010aware representations. However, there are still two limitations of these methods that hinder the progress of TOWE. Mainstream approaches typically utilize position indicators to mark the given target, which is a naive strategy and lacks task\u2010specific semantic meaning. Meanwhile, the annotated target\u2010opinion pairs contain rich latent structural knowledge from multiple perspectives, but existing methods only exploit the TOWE view. To tackle these issues, we formulate the TOWE task as a question answering (QA) problem and leverage a machine reading comprehension (MRC) model trained with a multiview paradigm to extract targeted opinions. Specifically, we introduce a template\u2010based pseudo\u2010question generation method and utilize deep attention interaction to build target\u2010aware context representations and extract related opinion words. To take advantage of latent structural correlations, we further cast the opinion\u2010target structure into three distinct yet correlated views and leverage meta\u2010learning to aggregate common knowledge among them to enhance the TOWE task. We evaluate the proposed model on four benchmark datasets, and our method achieves new state\u2010of\u2010the\u2010art results. Extensional experiments have shown that the pipeline method with our approach could surpass existing opinion pair extraction models, including joint methods that are usually believed to work better.<\/jats:p>","DOI":"10.1155\/2021\/6645871","type":"journal-article","created":{"date-parts":[[2021,3,31]],"date-time":"2021-03-31T01:50:05Z","timestamp":1617155405000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancement of Target\u2010Oriented Opinion Words Extraction with Multiview\u2010Trained Machine Reading Comprehension Model"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6644-4673","authenticated-orcid":false,"given":"Jingyuan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2138-845X","authenticated-orcid":false,"given":"Zequn","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5083-3578","authenticated-orcid":false,"given":"Zhi","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8833-4862","authenticated-orcid":false,"given":"Li","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7531-0909","authenticated-orcid":false,"given":"Kang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0592-171X","authenticated-orcid":false,"given":"Qing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2021,3,30]]},"reference":[{"key":"e_1_2_9_1_2","doi-asserted-by":"crossref","unstructured":"FanZ. WuZ. DaiX.-Y HuangS. andChenJ. Target-oriented opinion words extraction with target-fused neural sequence labeling 1 Proceedings of the 2019 Conference of the North NAACL-HLT 2019 June 2019 Minneapolis MN USA 2509\u20132518.","DOI":"10.18653\/v1\/N19-1259"},{"key":"e_1_2_9_2_2","unstructured":"TangD. QinB. FengX. andLiuT. Effective LSTMs for target-dependent sentiment classification Proceedings of the Conference: Technical Papers COLING 2016 26th International Conference on Computational Linguistics December 2016 Osaka Japan 3298\u20133307."},{"key":"e_1_2_9_3_2","doi-asserted-by":"crossref","unstructured":"WuZ. ZhaoF. DaiX.-Y HuangS. andChenJ. Latent opinions transfer network for target-oriented opinion words extraction Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence AAAI February 2020 New York NY USA.","DOI":"10.1609\/aaai.v34i05.6469"},{"key":"e_1_2_9_4_2","doi-asserted-by":"crossref","unstructured":"Ben VeysehA. P. NouriN. DernoncourtF. DouD. andHuu NguyenT. WebberB. CohnT. HeY. andLiuY. Introducing syntactic structures into target opinion word extraction with deep learning Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing EMNLP November 2020 Punta Cana Dominican Republic https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.719.","DOI":"10.18653\/v1\/2020.emnlp-main.719"},{"key":"e_1_2_9_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.07.152"},{"key":"e_1_2_9_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60450-9_50"},{"key":"e_1_2_9_7_2","doi-asserted-by":"crossref","unstructured":"DevlinJ. ChangM.-W. LeeK. andToutanovaK. BursteinJ. DoranC. andSolorioT. BERT: pre-training of deep bidirectional transformers for language understanding 1 Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies NAACL-HLT 2019 June 2019 Minneapolis MN USA https:\/\/doi.org\/10.18653\/v1\/n19-1423.","DOI":"10.18653\/v1\/N19-1423"},{"key":"e_1_2_9_8_2","doi-asserted-by":"crossref","unstructured":"HuM.andLiuB. Mining and summarizing customer reviews Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining August 2004 Seattle WA USA https:\/\/doi.org\/10.1145\/1014052.1014073.","DOI":"10.1145\/1014052.1014073"},{"key":"e_1_2_9_9_2","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00034"},{"key":"e_1_2_9_10_2","doi-asserted-by":"crossref","unstructured":"ChoiY. CardieC. RiloffE. andPatwardhanS. Identifying sources of opinions with conditional random fields and extraction patterns Proceedings of the Conference HLT\/EMNLP 2005 Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing October 2005 Vancouver Canada.","DOI":"10.3115\/1220575.1220620"},{"key":"e_1_2_9_11_2","unstructured":"YangB.andCardieC. Extracting opinion expressions with semi-markov conditional random fields Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning EMNLP-CoNLL July 2012 Jeju Island Korea."},{"key":"e_1_2_9_12_2","doi-asserted-by":"crossref","unstructured":"IrsoyO.andCardieC. Opinion mining with deep recurrent neural networks Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing EMNLP October 2014 Doha Qatar.","DOI":"10.3115\/v1\/D14-1080"},{"key":"e_1_2_9_13_2","doi-asserted-by":"crossref","unstructured":"LiuP. JotyS. R. andMengH. M. Fine-grained opinion mining with recurrent neural networks and word embeddings Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing EMNLP September 2015 Lisbon Portugal.","DOI":"10.18653\/v1\/D15-1168"},{"key":"e_1_2_9_14_2","doi-asserted-by":"crossref","unstructured":"WangW. PanS. J. DahlmeierD. andXiaoX. Coupled multi-layer attentions for co-extraction of aspect and opinion terms Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence February 2017 San Francisco CA USA 3316\u20133322.","DOI":"10.1609\/aaai.v31i1.10974"},{"key":"e_1_2_9_15_2","doi-asserted-by":"crossref","unstructured":"LiX.andLamW. Deep multi-task learning for aspect term extraction with memory interaction Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing EMNLP September 2017 Copenhagen Denmark.","DOI":"10.18653\/v1\/D17-1310"},{"key":"e_1_2_9_16_2","doi-asserted-by":"crossref","unstructured":"WangW. PanS. J. DahlmeierD. andXiaoX. Recursive neural conditional random fields for aspect-based sentiment analysis Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing EMNLP November 2016 Austin TX USA.","DOI":"10.18653\/v1\/D16-1059"},{"key":"e_1_2_9_17_2","doi-asserted-by":"crossref","unstructured":"DaiH.andSongY. Neural aspect and opinion term extraction with mined rules as weak supervision 1 Proceedings of the 57th Conference of the Association for Computational Linguistics ACL August 2019 Florence Italy.","DOI":"10.18653\/v1\/P19-1520"},{"key":"e_1_2_9_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2017.07.047"},{"key":"e_1_2_9_19_2","doi-asserted-by":"crossref","unstructured":"ZhuangL. JingF. andZhuX. Movie review mining and summarization Proceedings of the 2006 ACM CIKM International Conference on Information and Knowledge Management November 2006 Arlington VA USA https:\/\/doi.org\/10.1145\/1183614.1183625 2-s2.0-34547619773.","DOI":"10.1145\/1183614.1183625"},{"key":"e_1_2_9_20_2","doi-asserted-by":"crossref","unstructured":"RajpurkarP. ZhangJ. LopyrevK. andLiangP. SuJ. CarrerasX. andDuhK. Squad: 100 000+ questions for machine comprehension of text Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing EMNLP 2016 November 2016 Austin TX USA 2383\u20132392 https:\/\/doi.org\/10.18653\/v1\/d16-1264.","DOI":"10.18653\/v1\/D16-1264"},{"key":"e_1_2_9_21_2","unstructured":"SeoM. J. KembhaviA. AliF. andHajishirziH. Bidirectional attention flow for machine comprehension Proceedings of the 5th International Conference on Learning Representations ICLR 2017 April 2017 Toulon France."},{"key":"e_1_2_9_22_2","doi-asserted-by":"crossref","unstructured":"CuiY. ChenZ. WeiS. WangS. LiuT. andHuG. BarzilayR.andKanM.-Y. Attention-over-attention neural networks for reading comprehension 1 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics ACL 2017 August 2017 Vancouver Canada https:\/\/doi.org\/10.18653\/v1\/P17-1055 2-s2.0-85040927178.","DOI":"10.18653\/v1\/P17-1055"},{"key":"e_1_2_9_23_2","doi-asserted-by":"crossref","unstructured":"QiuL. ZhouH. QuY.et al. QA4IE: a question answering based framework for information extraction Proceedings of the Semantic Web-ISWC 2018-17th International Semantic Web Conference October 2018 Monterey CA USA https:\/\/doi.org\/10.1007\/978-3-030-00671-6_12 2-s2.0-85054834524.","DOI":"10.1007\/978-3-030-00671-6_12"},{"key":"e_1_2_9_24_2","doi-asserted-by":"crossref","unstructured":"LiX. FengJ. MengY. HanQ. WuF. andLiJ. JurafskyD. ChaiJ. SchluterN. andTetreaultJ. R. A unified MRC framework for named entity recognition Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics ACL 2020 July 2020 Seattle WA USA.","DOI":"10.18653\/v1\/2020.acl-main.519"},{"key":"e_1_2_9_25_2","doi-asserted-by":"crossref","unstructured":"ZhaoT. ZhaoY. CaoY. andLiZ. BessiereC. Asking effective and diverse questions: a machine reading comprehension based framework for joint entity-relation extraction Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence IJCAI 2020 July 2020 Yokohama Japan https:\/\/doi.org\/10.24963\/ijcai.2020\/546.","DOI":"10.24963\/ijcai.2020\/546"},{"key":"e_1_2_9_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2985126"},{"key":"e_1_2_9_27_2","doi-asserted-by":"crossref","unstructured":"LiuP. QiuX. andHuangX. Deep multi-task learning with shared memory 2016 https:\/\/arxiv.org\/abs\/1609.07222.","DOI":"10.18653\/v1\/D16-1012"},{"key":"e_1_2_9_28_2","doi-asserted-by":"crossref","unstructured":"LiuP. QiuX. andHuangX. Adversarial multi-task learning for text classification Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics ACL 2017 August 2017 Vancouver Canada https:\/\/doi.org\/10.18653\/v1\/P17-1001 2-s2.0-85040949558.","DOI":"10.18653\/v1\/P17-1001"},{"key":"e_1_2_9_29_2","doi-asserted-by":"crossref","unstructured":"CaoP. ChenY. LiuK. ZhaoJ. andLiuS. Adversarial transfer learning for Chinese named entity recognition with self-attention mechanism Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing November 2018 Brussels Belgium.","DOI":"10.18653\/v1\/D18-1017"},{"key":"e_1_2_9_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.07.017"},{"key":"e_1_2_9_31_2","doi-asserted-by":"crossref","unstructured":"WuF. LiuJ. WuC. HuangY. andXieX. LiuL. WhiteR. W. AminM.et al. Neural Chinese named entity recognition via CNN-LSTM-CRF and joint training with word segmentation Proceedings of the World Wide Web Conference WWW 2019 May 2019 San Francisco CA USA https:\/\/doi.org\/10.1145\/3308558.3313743 2-s2.0-85066884490.","DOI":"10.1145\/3308558.3313743"},{"key":"e_1_2_9_32_2","doi-asserted-by":"crossref","unstructured":"WangW.andPanS. J. Recursive neural structural correspondence network for cross-domain aspect and opinion co-extraction 1 Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics ACL 2018 July 2018 Melbourne Australia https:\/\/doi.org\/10.18653\/v1\/P18-1202.","DOI":"10.18653\/v1\/P18-1202"},{"key":"e_1_2_9_33_2","doi-asserted-by":"crossref","unstructured":"FeiH.andLiP. Cross-lingual unsupervised sentiment classification with multi-view transfer learning Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics ACL 2020 July 2020 Seattle WA USA.","DOI":"10.18653\/v1\/2020.acl-main.510"},{"key":"e_1_2_9_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2767818"},{"key":"e_1_2_9_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.06.087"},{"key":"e_1_2_9_36_2","unstructured":"FinnC. AbbeelP. LevineS. PrecupD. andTehY. W. Model-agnostic meta-learning for fast adaptation of deep networks Proceedings of the 34th International Conference on Machine Learning ICML 2017 August 2017 Sydney Australia."},{"key":"e_1_2_9_37_2","doi-asserted-by":"crossref","unstructured":"WangG. LuoC. SunX. XiongZ. andZengW. Tracking by instance detection: a meta-learning approach Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) June 2020 Seattle WA USA.","DOI":"10.1109\/CVPR42600.2020.00632"},{"key":"e_1_2_9_38_2","doi-asserted-by":"crossref","unstructured":"Perez-RuaJ.-M. ZhuX. HospedalesT. M. andXiangT. Incremental few-shot object detection Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) June 2020 Seattle WA USA.","DOI":"10.1109\/CVPR42600.2020.01386"},{"key":"e_1_2_9_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2019.2953465"},{"key":"e_1_2_9_40_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.05.007"},{"key":"e_1_2_9_41_2","doi-asserted-by":"crossref","unstructured":"JingL. ShangS. andShaoL. HuangY. KingI. LiuT.-Y. andVan SteenM. Metaner: named entity recognition with meta-learning Proceedings of the WWW\u201920: the Web Conference 2020 April 2020 Taipei Taiwan 429\u2013440 https:\/\/doi.org\/10.1145\/3366423.3380127.","DOI":"10.1145\/3366423.3380127"},{"key":"e_1_2_9_42_2","doi-asserted-by":"crossref","unstructured":"ObamuyideA.andVlachosA. AnnaK. TraumD. R. andM\u00e0rquezL. Model-agnostic meta-learning for relation classification with limited supervision Proceedings of the 57th Conference of the Association for Computational Linguistics ACL 2019 August 2019 Florence Italy https:\/\/doi.org\/10.18653\/v1\/p19-1589.","DOI":"10.18653\/v1\/P19-1589"},{"key":"e_1_2_9_43_2","doi-asserted-by":"crossref","unstructured":"HuX. MaF. LiuC. ZhangC. WenL. andYuP. S. Semi-supervised relation extraction via incremental meta self-training 2020 https:\/\/arxiv.org\/abs\/2010.16410.","DOI":"10.18653\/v1\/2021.findings-emnlp.44"},{"key":"e_1_2_9_44_2","unstructured":"VaswaniA. ShazeerN. ParmarN.et al. Attention is all you need Proceedings of the Annual Conference on Neural Information Processing Systems 2017 December 2017 Long Beach CA USA."},{"key":"e_1_2_9_45_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5724-z"},{"key":"e_1_2_9_46_2","unstructured":"KingmaD. P. BaJ. BengioY. andLeCunY. Adam: a method for stochastic optimization Proceedings of the 3rd International Conference on Learning Representations ICLR 2015 May 2015 San Diego CA USA."},{"key":"e_1_2_9_47_2","doi-asserted-by":"crossref","unstructured":"LiX. BingL. LiP. LamW. andYangZ. Aspect term extraction with history attention and selective transformation Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence IJCAI 2018 July 2018 Stockholm Sweden https:\/\/doi.org\/10.24963\/ijcai.2018\/583.","DOI":"10.24963\/ijcai.2018\/583"},{"key":"e_1_2_9_48_2","unstructured":"HeZ. HuangL. ZhangR. LuQ. andXueH. JurafskyD. ChaiJ. SchluterN. andTetreaultJ. R. Spanmlt: a span-based multi-task learning framework for pair-wise aspect and opinion terms extraction Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics ACL 2020 July 2020 Seattle WA USA."},{"key":"e_1_2_9_49_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2018.07.032"}],"container-title":["Computational Intelligence and Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/6645871.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/6645871.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2021\/6645871","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T11:42:18Z","timestamp":1722944538000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2021\/6645871"}},"subtitle":[],"editor":[{"given":"Ra\u015fit","family":"K\u00f6ker","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":49,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1155\/2021\/6645871"],"URL":"https:\/\/doi.org\/10.1155\/2021\/6645871","archive":["Portico"],"relation":{},"ISSN":["1687-5265","1687-5273"],"issn-type":[{"type":"print","value":"1687-5265"},{"type":"electronic","value":"1687-5273"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"2020-11-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-03-02","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-03-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"6645871"}}