{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T10:06:33Z","timestamp":1775815593470,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100021525","name":"Insight SFI Research Centre for Data Analytics","doi-asserted-by":"publisher","award":["12\/RC\/2289_P2"],"award-info":[{"award-number":["12\/RC\/2289_P2"]}],"id":[{"id":"10.13039\/501100021525","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761609","type":"proceedings-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:52:37Z","timestamp":1762563157000},"page":"6451-6455","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["From Rules to Flexibility: A Resource and Method for SEC Item Extraction in Post-2021 10-K Filings"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-6418-2354","authenticated-orcid":false,"given":"Xiao","family":"Li","sequence":"first","affiliation":[{"name":"University College Dublin, Dublin, Ireland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2565-592X","authenticated-orcid":false,"given":"Changhong","family":"Jin","sequence":"additional","affiliation":[{"name":"University College Dublin, Dublin, Ireland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2509-1370","authenticated-orcid":false,"given":"Ruihai","family":"Dong","sequence":"additional","affiliation":[{"name":"University College Dublin, Dublin, Ireland"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0254-8"},{"key":"e_1_3_2_1_2_1","volume-title":"Finbert: Financial sentiment analysis with pre-trained language models. arXiv preprint arXiv:1908.10063","author":"Araci Dogu","year":"2019","unstructured":"Dogu Araci. 2019. Finbert: Financial sentiment analysis with pre-trained language models. arXiv preprint arXiv:1908.10063 (2019)."},{"key":"e_1_3_2_1_3_1","volume-title":"A survey on metric learning for feature vectors and structured data. arXiv preprint arXiv:1306.6709","author":"Bellet Aur\u00e9lien","year":"2013","unstructured":"Aur\u00e9lien Bellet, Amaury Habrard, and Marc Sebban. 2013. A survey on metric learning for feature vectors and structured data. arXiv preprint arXiv:1306.6709 (2013)."},{"key":"e_1_3_2_1_4_1","volume-title":"Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150","author":"Beltagy Iz","year":"2020","unstructured":"Iz Beltagy, Matthew E Peters, and Arman Cohan. 2020. Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150 (2020)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-021-1076-7"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.2308\/ISYS-2020-011"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2020.113421"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3338906.3338909"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2018.06.008"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1111\/deci.12346"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2021.4156"},{"key":"e_1_3_2_1_13_1","volume-title":"Dynamic interpretation of emerging systemic risks. SSRN Electronic Journal","author":"Hanley Kathleen Weiss","year":"2016","unstructured":"Kathleen Weiss Hanley and Gerard Hoberg. 2016. Dynamic interpretation of emerging systemic risks. SSRN Electronic Journal (2016)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.2308\/AJPT-2019-517"},{"key":"e_1_3_2_1_15_1","volume-title":"Exploring the information contents of risk factors in SEC form 10-K: A multi-label text classification application. Available at SSRN 1784527","author":"Huang Ke-Wei","year":"2010","unstructured":"Ke-Wei Huang. 2010. Exploring the information contents of risk factors in SEC form 10-K: A multi-label text classification application. Available at SSRN 1784527 (2010)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1108\/DTA-05-2022-0215"},{"key":"e_1_3_2_1_17_1","unstructured":"Xiao Li Yang Xu Linyi Yang Yue Zhang and Ruihai Dong. 2024. NLP-Based Analysis of Annual Reports: Asset Volatility Prediction and Portfolio Strategy Application. (2024)."},{"key":"e_1_3_2_1_18_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1111\/1475-679X.12123"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","unstructured":"Lefteris Loukas Manos Fergadiotis Ion Androutsopoulos and Prodromos Malakasiotis. 2021. EDGAR-CORPUS: Billions of tokens make the world go round. (2021) 13-18. doi:10.18653\/v1\/2021.econlp-1.2","DOI":"10.18653\/v1\/2021.econlp-1.2"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.2308\/HORIZONS-2020-023"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2019.00047"},{"key":"e_1_3_2_1_23_1","volume-title":"StonkBERT: Can Language Models Predict Medium-Run Stock Price Movements? arXiv preprint arXiv:2202.02268","author":"Pasch Stefan","year":"2022","unstructured":"Stefan Pasch and Daniel Ehnes. 2022. StonkBERT: Can Language Models Predict Medium-Run Stock Price Movements? arXiv preprint arXiv:2202.02268 (2022)."},{"key":"e_1_3_2_1_24_1","volume-title":"Volatility prediction using financial disclosures sentiments with word embedding-based IR models. arXiv preprint arXiv:1702.01978","author":"Rekabsaz Navid","year":"2017","unstructured":"Navid Rekabsaz, Mihai Lupu, Artem Baklanov, Allan Hanbury, Alexander D\u00fcr, and Linda Anderson. 2017. Volatility prediction using financial disclosures sentiments with word embedding-based IR models. arXiv preprint arXiv:1702.01978 (2017)."},{"key":"e_1_3_2_1_25_1","unstructured":"Leonard Richardson. 2007. Beautiful soup documentation."},{"key":"e_1_3_2_1_26_1","volume-title":"More than words: Quantifying language to measure firms' fundamentals. The journal of finance","author":"Tetlock Paul C","year":"2008","unstructured":"Paul C Tetlock, Maytal Saar-Tsechansky, and Sofus Macskassy. 2008. More than words: Quantifying language to measure firms' fundamentals. The journal of finance, Vol. 63, 3 (2008), 1437-1467."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2948072"},{"key":"e_1_3_2_1_28_1","volume-title":"Rule-based information extraction: Advantages, limitations, and perspectives. Jusletter IT (02","author":"Waltl Bernhard","year":"2018","unstructured":"Bernhard Waltl, Georg Bonczek, and Florian Matthes. 2018. Rule-based information extraction: Advantages, limitations, and perspectives. Jusletter IT (02 2018), Vol. 4 (2018)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-021-10033-1"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3481989"}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","location":"Seoul Republic of Korea","acronym":"CIKM '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T02:29:46Z","timestamp":1765506586000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761609"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":30,"alternative-id":["10.1145\/3746252.3761609","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761609","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}