{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T19:39:28Z","timestamp":1771616368495,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,21]]},"DOI":"10.1145\/3627673.3680009","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T19:34:21Z","timestamp":1729452861000},"page":"4324-4331","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Boosting Entity Recognition by leveraging Cross-task Domain Models for Weak Supervision"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7658-7532","authenticated-orcid":false,"given":"Sanjay","family":"Agrawal","sequence":"first","affiliation":[{"name":"Amazon.com Inc., Bengaluru, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7849-9743","authenticated-orcid":false,"given":"Srujana","family":"Merugu","sequence":"additional","affiliation":[{"name":"Amazon.com Inc., Bengaluru, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6787-1383","authenticated-orcid":false,"given":"Vivek","family":"Sembium","sequence":"additional","affiliation":[{"name":"Amazon.com Inc., Bengaluru, India"}]}],"member":"320","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"HISS: A novel hybrid inference architecture in embedding based product sourcing using knowledge distillation.","author":"Ankith MS","year":"2022","unstructured":"MS Ankith, Sourab Mangrulkar, and Vivek Sembium. 2022. HISS: A novel hybrid inference architecture in embedding based product sourcing using knowledge distillation. (2022)."},{"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","doi-asserted-by":"crossref","unstructured":"Iz Beltagy Kyle Lo and Arman Cohan. 2019. SciBERT: Pretrained Language Model for Scientific Text. In EMNLP. arXiv:arXiv:1903.10676","DOI":"10.18653\/v1\/D19-1371"},{"key":"e_1_3_2_1_4_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 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_5_1","volume-title":"Lowresource name tagging learned with weakly labeled data. arXiv preprint arXiv:1908.09659","author":"Cao Yixin","year":"2019","unstructured":"Yixin Cao, Zikun Hu, Tat-seng Chua, Zhiyuan Liu, and Heng Ji. 2019. Lowresource name tagging learned with weakly labeled data. arXiv preprint arXiv:1908.09659 (2019)."},{"key":"e_1_3_2_1_6_1","volume-title":"Prompt-Based Metric Learning for Few-Shot NER. arXiv preprint arXiv:2211.04337","author":"Chen Yanru","year":"2022","unstructured":"Yanru Chen, Yanan Zheng, and Zhilin Yang. 2022. Prompt-Based Metric Learning for Few-Shot NER. arXiv preprint arXiv:2211.04337 (2022)."},{"key":"e_1_3_2_1_7_1","volume-title":"ARTICLE","author":"Collobert Ronan","year":"2011","unstructured":"Ronan Collobert, JasonWeston, L\u00e9on Bottou, Michael Karlen, Koray Kavukcuoglu, and Pavel Kuksa. 2011. Natural language processing (almost) from scratch. Journal of machine learning research 12, ARTICLE (2011), 2493--2537."},{"key":"e_1_3_2_1_8_1","volume-title":"Modelling radiological language with bidirectional long short-term memory networks. arXiv preprint arXiv:1609.08409","author":"Cornegruta Savelie","year":"2016","unstructured":"Savelie Cornegruta, Robert Bakewell, Samuel Withey, and Giovanni Montana. 2016. Modelling radiological language with bidirectional long short-term memory networks. arXiv preprint arXiv:1609.08409 (2016)."},{"key":"e_1_3_2_1_9_1","volume-title":"d.]. Template-based named entity recognition using BART. arXiv","author":"Cui L","year":"2021","unstructured":"L Cui, Y Wu, J Liu, S Yang, and Y Zhang. [n. d.]. Template-based named entity recognition using BART. arXiv 2021. arXiv preprint arXiv:2106.01760 ([n. d.])."},{"key":"e_1_3_2_1_10_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_11_1","volume-title":"Self-training improves pre-training for natural language understanding. arXiv preprint arXiv:2010.02194","author":"Du Jingfei","year":"2020","unstructured":"Jingfei Du, Edouard Grave, Beliz Gunel, Vishrav Chaudhary, Onur Celebi, Michael Auli, Ves Stoyanov, and Alexis Conneau. 2020. Self-training improves pre-training for natural language understanding. arXiv preprint arXiv:2010.02194 (2020)."},{"key":"e_1_3_2_1_12_1","unstructured":"Martin Ester Hans-Peter Kriegel J\u00f6rg Sander Xiaowei Xu et al. 1996. A densitybased algorithm for discovering clusters in large spatial databases with noise.. In kdd Vol. 96. 226--231."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the Workshop on Computational lexicography and Multimedia Dictionaries (COMLEX","author":"Farmakiotou Dimitra","year":"2000","unstructured":"Dimitra Farmakiotou, Vangelis Karkaletsis, John Koutsias, George Sigletos, Constantine D Spyropoulos, and Panagiotis Stamatopoulos. 2000. Rule-based named entity recognition for Greek financial texts. In Proceedings of the Workshop on Computational lexicography and Multimedia Dictionaries (COMLEX 2000). 75--78."},{"key":"e_1_3_2_1_14_1","volume-title":"How to tackle an emerging topic? Combining strong and weak labels for Covid news NER. arXiv preprint arXiv:2209.15108","author":"Ficek Aleksander","year":"2022","unstructured":"Aleksander Ficek, Fangyu Liu, and Nigel Collier. 2022. How to tackle an emerging topic? Combining strong and weak labels for Covid news NER. arXiv preprint arXiv:2209.15108 (2022)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297280.3297378"},{"key":"e_1_3_2_1_16_1","volume-title":"Robust lexical features for improved neural network named-entity recognition. arXiv preprint arXiv:1806.03489","author":"Ghaddar Abbas","year":"2018","unstructured":"Abbas Ghaddar and Philippe Langlais. 2018. Robust lexical features for improved neural network named-entity recognition. arXiv preprint arXiv:1806.03489 (2018)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10894"},{"key":"e_1_3_2_1_18_1","volume-title":"KeyBERT: Minimal keyword extraction with BERT. Zenodo","author":"Grootendorst Maarten","year":"2020","unstructured":"Maarten Grootendorst. 2020. KeyBERT: Minimal keyword extraction with BERT. Zenodo (2020)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458754"},{"key":"e_1_3_2_1_20_1","volume-title":"ANEA: distant supervision for low-resource named entity recognition. arXiv preprint arXiv:2102.13129","author":"Hedderich Michael A","year":"2021","unstructured":"Michael A Hedderich, Lukas Lange, and Dietrich Klakow. 2021. ANEA: distant supervision for low-resource named entity recognition. arXiv preprint arXiv:2102.13129 (2021)."},{"key":"e_1_3_2_1_21_1","volume-title":"Bidirectional LSTM-CRF models for sequence tagging. arXiv preprint arXiv:1508.01991","author":"Huang Zhiheng","year":"2015","unstructured":"Zhiheng Huang, Wei Xu, and Kai Yu. 2015. Bidirectional LSTM-CRF models for sequence tagging. arXiv preprint arXiv:1508.01991 (2015)."},{"key":"e_1_3_2_1_22_1","unstructured":"John Lafferty Andrew McCallum and Fernando CN Pereira. 2001. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. (2001)."},{"key":"e_1_3_2_1_23_1","volume-title":"Neural architectures for named entity recognition. arXiv preprint arXiv:1603.01360","author":"Lample Guillaume","year":"2016","unstructured":"Guillaume Lample, Miguel Ballesteros, Sandeep Subramanian, Kazuya Kawakami, and Chris Dyer. 2016. Neural architectures for named entity recognition. arXiv preprint arXiv:1603.01360 (2016)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3038670"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380127"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2396761.2398506"},{"key":"e_1_3_2_1_28_1","volume-title":"BERTifying the hidden Markov model for multi-source weakly supervised named entity recognition. arXiv preprint arXiv:2105.12848","author":"Li Yinghao","year":"2021","unstructured":"Yinghao Li, Pranav Shetty, Lucas Liu, Chao Zhang, and Le Song. 2021. BERTifying the hidden Markov model for multi-source weakly supervised named entity recognition. arXiv preprint arXiv:2105.12848 (2021)."},{"key":"e_1_3_2_1_29_1","unstructured":"Nut Limsopatham and Nigel Henry Collier. 2016. Bidirectional LSTM for named entity recognition in Twitter messages. (2016)."},{"key":"e_1_3_2_1_30_1","volume-title":"Named entity recognition without labelled data: A weak supervision approach. arXiv preprint arXiv:2004.14723","author":"Lison Pierre","year":"2020","unstructured":"Pierre Lison, Aliaksandr Hubin, Jeremy Barnes, and Samia Touileb. 2020. Named entity recognition without labelled data: A weak supervision approach. arXiv preprint arXiv:2004.14723 (2020)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2100"},{"key":"e_1_3_2_1_32_1","article-title":"Generalized Expectation Criteria for Semi-Supervised Learning with Weakly Labeled Data","volume":"11","author":"Mann Gideon S","year":"2010","unstructured":"Gideon S Mann and Andrew McCallum. 2010. Generalized Expectation Criteria for Semi-Supervised Learning with Weakly Labeled Data. Journal of machine learning research 11, 2 (2010).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the Australasian language technology workshop","author":"Moll\u00e1 Diego","year":"2006","unstructured":"Diego Moll\u00e1, Menno Van Zaanen, and Daniel Smith. 2006. Named entity recognition for question answering. In Proceedings of the Australasian language technology workshop 2006. 51--58."},{"key":"e_1_3_2_1_34_1","first-page":"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, Peter J Liu, et al. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21, 140 (2020), 1--67.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12008"},{"key":"e_1_3_2_1_36_1","volume-title":"Introduction to the CoNLL-2003 shared task: Language-independent named entity recognition. arXiv preprint cs\/0306050","author":"Sang Erik F","year":"2003","unstructured":"Erik F Sang and Fien De Meulder. 2003. Introduction to the CoNLL-2003 shared task: Language-independent named entity recognition. arXiv preprint cs\/0306050 (2003)."},{"key":"e_1_3_2_1_37_1","volume-title":"Learning named entity tagger using domain-specific dictionary. arXiv preprint arXiv:1809.03599","author":"Shang Jingbo","year":"2018","unstructured":"Jingbo Shang, Liyuan Liu, Xiang Ren, Xiaotao Gu, Teng Ren, and Jiawei Han. 2018. Learning named entity tagger using domain-specific dictionary. arXiv preprint arXiv:1809.03599 (2018)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6415"},{"key":"e_1_3_2_1_39_1","volume-title":"Prototypical networks for few-shot learning. Advances in neural information processing systems 30","author":"Snell Jake","year":"2017","unstructured":"Jake Snell, Kevin Swersky, and Richard Zemel. 2017. Prototypical networks for few-shot learning. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2015.06.007"},{"key":"e_1_3_2_1_41_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_42_1","volume-title":"Software engineering research conference","author":"Wang Rui","unstructured":"Rui Wang, Wei Liu, and Chris McDonald. 2014. Corpus-independent generic keyphrase extraction using word embedding vectors. In Software engineering research conference, Vol. 39. 1--8."},{"key":"e_1_3_2_1_43_1","volume-title":"Crossweigh: Training named entity tagger from imperfect annotations. arXiv preprint arXiv:1909.01441","author":"Wang Zihan","year":"2019","unstructured":"Zihan Wang, Jingbo Shang, Liyuan Liu, Lihao Lu, Jiacheng Liu, and Jiawei Han. 2019. Crossweigh: Training named entity tagger from imperfect annotations. arXiv preprint arXiv:1909.01441 (2019)."},{"key":"e_1_3_2_1_44_1","volume-title":"Proceedings of the Clinical Natural Language Processing Workshop (ClinicalNLP). 1--6.","author":"Casillas Arantza","year":"2016","unstructured":"RebeckaWeegar, Arantza Casillas, Arantza D\u00edaz de Ilarraza, Maite Oronoz, Alicia P\u00e9rez, and Koldo Gojenola. 2016. The impact of simple feature engineering in multilingual medical NER. In Proceedings of the Clinical Natural Language Processing Workshop (ClinicalNLP). 1--6."},{"key":"e_1_3_2_1_45_1","volume-title":"Carolyn J Mattingly, Jiao Li, Thomas C Wiegers, and Zhiyong Lu.","author":"Wei Chih-Hsuan","year":"2016","unstructured":"Chih-Hsuan Wei, Yifan Peng, Robert Leaman, Allan Peter Davis, Carolyn J Mattingly, Jiao Li, Thomas C Wiegers, and Zhiyong Lu. 2016. Assessing the state of the art in biomedical relation extraction: overview of the BioCreative V chemicaldisease relation (CDR) task. Database 2016 (2016)."},{"key":"e_1_3_2_1_46_1","volume-title":"Simple and effective few-shot named entity recognition with structured nearest neighbor learning. arXiv preprint arXiv:2010.02405","author":"Yang Yi","year":"2020","unstructured":"Yi Yang and Arzoo Katiyar. 2020. Simple and effective few-shot named entity recognition with structured nearest neighbor learning. arXiv preprint arXiv:2010.02405 (2020)."},{"key":"e_1_3_2_1_47_1","first-page":"609","article-title":"Obtaining calibrated probability estimates from decision trees and naive bayesian classifiers","volume":"1","author":"Zadrozny Bianca","year":"2001","unstructured":"Bianca Zadrozny and Charles Elkan. 2001. Obtaining calibrated probability estimates from decision trees and naive bayesian classifiers. In Icml, Vol. 1. 609--616.","journal-title":"Icml"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21425"}],"event":{"name":"CIKM '24: The 33rd ACM International Conference on Information and Knowledge Management","location":"Boise ID USA","acronym":"CIKM '24","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 33rd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3680009","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627673.3680009","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:17Z","timestamp":1750294697000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3680009"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":48,"alternative-id":["10.1145\/3627673.3680009","10.1145\/3627673"],"URL":"https:\/\/doi.org\/10.1145\/3627673.3680009","relation":{},"subject":[],"published":{"date-parts":[[2024,10,21]]},"assertion":[{"value":"2024-10-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}