{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T17:18:31Z","timestamp":1778606311585,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3613776","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"8571-8579","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["AbCoRD: Exploiting multimodal generative approach for Aspect-based Complaint and Rationale Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5422-9498","authenticated-orcid":false,"given":"Raghav","family":"Jain","sequence":"first","affiliation":[{"name":"Indian Institute of Technology Patna, Patna, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2020-4751","authenticated-orcid":false,"given":"Apoorva","family":"Singh","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Patna, Patna, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7206-7294","authenticated-orcid":false,"given":"Vivek","family":"Gangwar","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Patna, Patna, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5458-9381","authenticated-orcid":false,"given":"Sriparna","family":"Saha","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Patna, Patna, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"International Conference on Intelligent Text Processing and Computational Linguistics. Springer, 246--257","author":"Akhtar Md Shad","year":"2016","unstructured":"Md Shad Akhtar, Asif Ekbal, and Pushpak Bhattacharyya. 2016. Aspect based sentiment analysis: category detection and sentiment classification for Hindi. In International Conference on Intelligent Text Processing and Computational Linguistics. Springer, 246--257."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-srw.20"},{"key":"e_1_3_2_1_3_1","volume-title":"Inter-coder agreement for computational linguistics. Computational linguistics","author":"Artstein Ron","year":"2008","unstructured":"Ron Artstein and Massimo Poesio. 2008. Inter-coder agreement for computational linguistics. Computational linguistics, Vol. 34, 4 (2008), 555--596."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v11i1.14919"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511813085"},{"key":"e_1_3_2_1_6_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2007.10.010"},{"key":"e_1_3_2_1_8_1","volume-title":"Multi-task learning with deep neural networks: A survey. arXiv preprint arXiv:2009.09796","author":"Crawshaw Michael","year":"2020","unstructured":"Michael Crawshaw. 2020. Multi-task learning with deep neural networks: A survey. arXiv preprint arXiv:2009.09796 (2020)."},{"key":"e_1_3_2_1_9_1","volume-title":"Measuring nominal scale agreement among many raters. Psychological bulletin","author":"Fleiss Joseph L","year":"1971","unstructured":"Joseph L Fleiss. 1971. Measuring nominal scale agreement among many raters. Psychological bulletin, Vol. 76, 5 (1971), 378."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.9790\/0837-1763441"},{"key":"e_1_3_2_1_11_1","volume-title":"Education","volume":"99","author":"Jenkins William M","year":"1979","unstructured":"William M Jenkins and Joseph P Cangemi. 1979. Levels of Intensity of Dissatisfaction: A Model. Education, Vol. 99, 4 (1979)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.180"},{"key":"e_1_3_2_1_13_1","volume-title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans. arxiv","author":"Joshi Mandar","year":"1907","unstructured":"Mandar Joshi, Danqi Chen, Yinhan Liu, Daniel S. Weld, Luke Zettlemoyer, and Omer Levy. 2020. SpanBERT: Improving Pre-training by Representing and Predicting Spans. arxiv: 1907.10529 [cs.CL]"},{"key":"e_1_3_2_1_14_1","volume-title":"Supervised Multimodal Bitransformers for Classifying Images and Text. arxiv","author":"Kiela Douwe","year":"1909","unstructured":"Douwe Kiela, Suvrat Bhooshan, Hamed Firooz, Ethan Perez, and Davide Testuggine. 2020. Supervised Multimodal Bitransformers for Classifying Images and Text. arxiv: 1909.02950 [cs.CL]"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"M Lailiyah S Sumpeno and IK E Purnama. 2017. Sentiment analysis of public complaints using lexical resources between Indonesian sentiment lexicon and Sentiwordnet. In 2017 International Seminar on Intelligent Technology and Its Applications (ISITIA). IEEE 307--312.","DOI":"10.1109\/ISITIA.2017.8124100"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.08.069"},{"key":"e_1_3_2_1_17_1","volume-title":"Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461","author":"Lewis Mike","year":"2019","unstructured":"Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, and Luke Zettlemoyer. 2019. Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461 (2019)."},{"key":"e_1_3_2_1_18_1","volume-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems","author":"Lu Jiasen","year":"2019","unstructured":"Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_19_1","volume-title":"Complaints: A Study of Speech Act Behavior among Native and Nonnative Speakers of Hebrew. The Prag-matic Perspective.","author":"Olshtain E","year":"1985","unstructured":"E Olshtain and L Weinbach. 1985. Complaints: A Study of Speech Act Behavior among Native and Nonnative Speakers of Hebrew. The Prag-matic Perspective."},{"key":"e_1_3_2_1_20_1","volume-title":"Meld: A multimodal multi-party dataset for emotion recognition in conversations. arXiv preprint arXiv:1810.02508","author":"Poria Soujanya","year":"2018","unstructured":"Soujanya Poria, Devamanyu Hazarika, Navonil Majumder, Gautam Naik, Erik Cambria, and Rada Mihalcea. 2018. Meld: A multimodal multi-party dataset for emotion recognition in conversations. arXiv preprint arXiv:1810.02508 (2018)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-021-09925-7"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1495"},{"key":"e_1_3_2_1_23_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1910.10683"},{"key":"e_1_3_2_1_25_1","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. J. Mach. Learn. Res., Vol. 21 (2020), 140:1--140:67. http:\/\/jmlr.org\/papers\/v21\/20-074.html","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_1_26_1","volume-title":"100,000 questions for machine comprehension of text. arXiv preprint arXiv:1606.05250","author":"Rajpurkar Pranav","year":"2016","unstructured":"Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. Squad: 100,000 questions for machine comprehension of text. arXiv preprint arXiv:1606.05250 (2016)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.456"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i11.21476"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-28238-6_9"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-99736-6_29"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86331-9_46"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.59"},{"key":"e_1_3_2_1_33_1","volume-title":"Interlanguage pragmatics: Requests, complaints, and apologies","author":"Trosborg Anna","unstructured":"Anna Trosborg. 2011. Interlanguage pragmatics: Requests, complaints, and apologies. Vol. 7. Walter de Gruyter."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.pragma.2010.11.007"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/34.1-2.1"},{"key":"e_1_3_2_1_36_1","volume-title":"Automating Knowledge Distillation and Representation from Richly Formatted Data","author":"Sen Wu.","unstructured":"Sen Wu. 2020. Automating Knowledge Distillation and Representation from Richly Formatted Data. Stanford University."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-2008"},{"key":"e_1_3_2_1_38_1","unstructured":"Ron Zhu. 2020. Enhance Multimodal Transformer With External Label And In-Domain Pretrain: Hateful Meme Challenge Winning Solution."}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3613776","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3613776","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:07:16Z","timestamp":1755821236000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3613776"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":38,"alternative-id":["10.1145\/3581783.3613776","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3613776","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}