{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T04:00:42Z","timestamp":1772164842694,"version":"3.50.1"},"reference-count":18,"publisher":"China Science Publishing & Media Ltd.","issue":"3","license":[{"start":{"date-parts":[[2021,5,11]],"date-time":"2021-05-11T00:00:00Z","timestamp":1620691200000},"content-version":"vor","delay-in-days":130,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,9,8]]},"abstract":"<jats:p>This paper presents a winning solution for the CCKS-2020 financial event extraction task, where the goal is to identify event types, triggers and arguments in sentences across multiple event types. In this task, we focus on resolving two challenging problems (i.e., low resources and element overlapping) by proposing a joint learning framework, named SaltyFishes. We first formulate the event extraction task as a joint probability model. By sharing parameters in the model across different types, we can learn to adapt to low-resource events based on high-resource events. We further address the element overlapping problems by a mechanism of Conditional Layer Normalization, achieving even better extraction accuracy. The overall approach achieves an F1-score of 87.8% which ranks the first place in the competition.<\/jats:p>","DOI":"10.1162\/dint_a_00098","type":"journal-article","created":{"date-parts":[[2021,5,11]],"date-time":"2021-05-11T19:43:26Z","timestamp":1620762206000},"page":"444-459","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":8,"title":["A Joint Learning Framework for the CCKS-2020 Financial Event Extraction Task"],"prefix":"10.3724","volume":"3","author":[{"given":"Jiawei","family":"Sheng","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China"},{"name":"School of Cyber Security, University of Chinese Academy of Sciences, Beijing 100049, China"}]},{"given":"Qian","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, Beihang University, Beijing 100191, China"}]},{"given":"Yiming","family":"Hei","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Beihang University, Beijing 100191, China"}]},{"given":"Shu","family":"Guo","sequence":"additional","affiliation":[{"name":"National Computer Network Emergency Response Technical Team\/Coordination Center of China, Beijing 100029, China"}]},{"given":"Bowen","family":"Yu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China"},{"name":"School of Cyber Security, University of Chinese Academy of Sciences, Beijing 100049, China"}]},{"given":"Lihong","family":"Wang","sequence":"additional","affiliation":[{"name":"National Computer Network Emergency Response Technical Team\/Coordination Center of China, Beijing 100029, China"}]},{"given":"Min","family":"He","sequence":"additional","affiliation":[{"name":"National Computer Network Emergency Response Technical Team\/Coordination Center of China, Beijing 100029, China"}]},{"given":"Tingwen","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China"},{"name":"School of Cyber Security, University of Chinese Academy of Sciences, Beijing 100049, China"}]},{"given":"Hongbo","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China"},{"name":"School of Cyber Security, University of Chinese Academy of Sciences, Beijing 100049, China"}]}],"member":"2026","published-online":{"date-parts":[[2021,9,8]]},"reference":[{"key":"2021102914233736600_ref1","first-page":"167","article-title":"Event extraction via dynamic multi-pooling convolutional neural networks","volume-title":"Proceedings of the Annual Meeting of the Association for Computational Linguistics","author":"Chen","year":"2015"},{"key":"2021102914233736600_ref2","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1145\/3336191.3371796","article-title":"Meta-learning with dynamic-memory-based prototypical network for few-shot event detection","volume-title":"WSDM '20: Proceedings of the 13th International Conference on Web Search and Data Mining","author":"Deng","year":"2020"},{"key":"2021102914233736600_ref3","first-page":"2160","article-title":"Zero-shot transfer learning for event extraction","volume-title":"Proceedings of the Annual Meeting of the Association for Computational Linguistics","author":"Huang","year":"2018"},{"key":"2021102914233736600_ref4","first-page":"300","article-title":"Joint event extraction via recurrent neural networks","volume-title":"Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)","author":"Nguyen","year":"2016"},{"key":"2021102914233736600_ref5","first-page":"6851","article-title":"One for all: Neural joint modeling of entities and events","volume-title":"The 33rd AAAI Conference on Artificial Intelligence (AAAI-19)","author":"Nguyen","year":"2019"},{"key":"2021102914233736600_ref6","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)","author":"Devlin","year":"2019"},{"key":"2021102914233736600_ref7","first-page":"73","article-title":"Joint event extraction via structured prediction with global features","volume-title":"Proceedings of the Annual Meeting of the Association for Computational Linguistics","author":"Li","year":"2013"},{"key":"2021102914233736600_ref8","doi-asserted-by":"crossref","first-page":"1247","DOI":"10.18653\/v1\/D18-1156","article-title":"Jointly multiple events extraction via attention-based graph information aggregation","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Liu","year":"2018"},{"key":"2021102914233736600_ref9","first-page":"5916","article-title":"Jointly extracting event triggers and arguments by dependency-bridge RNN and tensor-based argument interaction","volume-title":"The 32nd AAAI Conference on Artificial Intelligence (AAAI-18)","author":"Sha","year":"2018"},{"key":"2021102914233736600_ref10","doi-asserted-by":"crossref","first-page":"671","DOI":"10.18653\/v1\/2020.emnlp-main.49","article-title":"Event extraction by answering (almost) natural questions","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Du","year":"2020"},{"key":"2021102914233736600_ref11","first-page":"829","article-title":"Event extraction as multi-turn question answering","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Li","year":"2020"},{"key":"2021102914233736600_ref12","doi-asserted-by":"crossref","first-page":"1641","DOI":"10.18653\/v1\/2020.emnlp-main.128","article-title":"Event extraction as machine reading comprehension","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Liu","year":"2020"},{"key":"2021102914233736600_ref13","first-page":"5783","article-title":"Entity, relation, and event extraction with contextualized span representations","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Wadden","year":"2019"},{"key":"2021102914233736600_ref14","first-page":"5284","article-title":"Exploring pre-trained language models for event extraction and generation","volume-title":"Proceedings of the Annual Meeting of the Association for Computational Linguistics","author":"Yang","year":"2019"},{"key":"2021102914233736600_ref15","doi-asserted-by":"crossref","first-page":"707","DOI":"10.18653\/v1\/2020.emnlp-main.52","article-title":"Incremental event detection via knowledge consolidation networks","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Cao","year":"2020"},{"key":"2021102914233736600_ref16","volume-title":"Conditional text generation based on conditional layer normalization (in Chinese)","author":"Su","year":"2021"},{"key":"2021102914233736600_ref17","doi-asserted-by":"crossref","DOI":"10.1145\/3442381.3450029","volume-title":"Semi-open information extraction","author":"Yu","year":"2021"},{"key":"2021102914233736600_ref18","volume-title":"Layer normalization","author":"Ba","year":"2016"}],"container-title":["Data Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/direct.mit.edu\/dint\/article-pdf\/3\/3\/444\/1969122\/dint_a_00098.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/direct.mit.edu\/dint\/article-pdf\/3\/3\/444\/1969122\/dint_a_00098.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,14]],"date-time":"2025-03-14T03:43:04Z","timestamp":1741923784000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.sciengine.com\/doi\/10.1162\/dint_a_00098"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":18,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2021,9,8]]}},"URL":"https:\/\/doi.org\/10.1162\/dint_a_00098","relation":{"is-referenced-by":[{"id-type":"doi","id":"10.1038\/s41598-025-23093-w","asserted-by":"object"}]},"ISSN":["2641-435X"],"issn-type":[{"value":"2641-435X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021]]},"published":{"date-parts":[[2021]]}}}