MedJEx: A Medical Jargon Extraction Model with Wiki's Hyperlink Span and Contextualized Masked Language Model Score. Kwon, S., Yao, Z., Jordan, H., Levy, D., Corner, B., & Yu, H. In Goldberg, Y., Kozareva, Z., & Zhang, Y., editors, Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 11733–11751, Abu Dhabi, United Arab Emirates, December, 2022. Association for Computational Linguistics. ![MedJEx: A Medical Jargon Extraction Model with Wiki's Hyperlink Span and Contextualized Masked Language Model Score [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex This paper proposes a new natural language processing (NLP) application for identifying medical jargon terms potentially difficult for patients to comprehend from electronic health record (EHR) notes. We first present a novel and publicly available dataset with expert-annotated medical jargon terms from 18K+ EHR note sentences (MedJ). Then, we introduce a novel medical jargon extraction (MedJEx) model which has been shown to outperform existing state-of-the-art NLP models. First, MedJEx improved the overall performance when it was trained on an auxiliary Wikipedia hyperlink span dataset, where hyperlink spans provide additional Wikipedia articles to explain the spans (or terms), and then fine-tuned on the annotated MedJ data. Secondly, we found that a contextualized masked language model score was beneficial for detecting domain-specific unfamiliar jargon terms. Moreover, our results show that training on the auxiliary Wikipedia hyperlink span datasets improved six out of eight biomedical named entity recognition benchmark datasets. MedJEx is publicly available.
@inproceedings{kwon_medjex_2022,
address = {Abu Dhabi, United Arab Emirates},
title = {{MedJEx}: {A} {Medical} {Jargon} {Extraction} {Model} with {Wiki}'s {Hyperlink} {Span} and {Contextualized} {Masked} {Language} {Model} {Score}},
shorttitle = {{MedJEx}},
url = {https://aclanthology.org/2022.emnlp-main.805},
doi = {10.18653/v1/2022.emnlp-main.805},
abstract = {This paper proposes a new natural language processing (NLP) application for identifying medical jargon terms potentially difficult for patients to comprehend from electronic health record (EHR) notes. We first present a novel and publicly available dataset with expert-annotated medical jargon terms from 18K+ EHR note sentences (MedJ). Then, we introduce a novel medical jargon extraction (MedJEx) model which has been shown to outperform existing state-of-the-art NLP models. First, MedJEx improved the overall performance when it was trained on an auxiliary Wikipedia hyperlink span dataset, where hyperlink spans provide additional Wikipedia articles to explain the spans (or terms), and then fine-tuned on the annotated MedJ data. Secondly, we found that a contextualized masked language model score was beneficial for detecting domain-specific unfamiliar jargon terms. Moreover, our results show that training on the auxiliary Wikipedia hyperlink span datasets improved six out of eight biomedical named entity recognition benchmark datasets. MedJEx is publicly available.},
urldate = {2024-01-03},
booktitle = {Proceedings of the 2022 {Conference} on {Empirical} {Methods} in {Natural} {Language} {Processing}},
publisher = {Association for Computational Linguistics},
author = {Kwon, Sunjae and Yao, Zonghai and Jordan, Harmon and Levy, David and Corner, Brian and Yu, Hong},
editor = {Goldberg, Yoav and Kozareva, Zornitsa and Zhang, Yue},
month = dec,
year = {2022},
keywords = {notion},
pages = {11733--11751},
}
Downloads: 0
{"_id":"qjX5pJCWCxcgSELoB","bibbaseid":"kwon-yao-jordan-levy-corner-yu-medjexamedicaljargonextractionmodelwithwikishyperlinkspanandcontextualizedmaskedlanguagemodelscore-2022","author_short":["Kwon, S.","Yao, Z.","Jordan, H.","Levy, D.","Corner, B.","Yu, H."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"Abu Dhabi, United Arab Emirates","title":"MedJEx: A Medical Jargon Extraction Model with Wiki's Hyperlink Span and Contextualized Masked Language Model Score","shorttitle":"MedJEx","url":"https://aclanthology.org/2022.emnlp-main.805","doi":"10.18653/v1/2022.emnlp-main.805","abstract":"This paper proposes a new natural language processing (NLP) application for identifying medical jargon terms potentially difficult for patients to comprehend from electronic health record (EHR) notes. We first present a novel and publicly available dataset with expert-annotated medical jargon terms from 18K+ EHR note sentences (MedJ). Then, we introduce a novel medical jargon extraction (MedJEx) model which has been shown to outperform existing state-of-the-art NLP models. First, MedJEx improved the overall performance when it was trained on an auxiliary Wikipedia hyperlink span dataset, where hyperlink spans provide additional Wikipedia articles to explain the spans (or terms), and then fine-tuned on the annotated MedJ data. Secondly, we found that a contextualized masked language model score was beneficial for detecting domain-specific unfamiliar jargon terms. Moreover, our results show that training on the auxiliary Wikipedia hyperlink span datasets improved six out of eight biomedical named entity recognition benchmark datasets. MedJEx is publicly available.","urldate":"2024-01-03","booktitle":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","publisher":"Association for Computational Linguistics","author":[{"propositions":[],"lastnames":["Kwon"],"firstnames":["Sunjae"],"suffixes":[]},{"propositions":[],"lastnames":["Yao"],"firstnames":["Zonghai"],"suffixes":[]},{"propositions":[],"lastnames":["Jordan"],"firstnames":["Harmon"],"suffixes":[]},{"propositions":[],"lastnames":["Levy"],"firstnames":["David"],"suffixes":[]},{"propositions":[],"lastnames":["Corner"],"firstnames":["Brian"],"suffixes":[]},{"propositions":[],"lastnames":["Yu"],"firstnames":["Hong"],"suffixes":[]}],"editor":[{"propositions":[],"lastnames":["Goldberg"],"firstnames":["Yoav"],"suffixes":[]},{"propositions":[],"lastnames":["Kozareva"],"firstnames":["Zornitsa"],"suffixes":[]},{"propositions":[],"lastnames":["Zhang"],"firstnames":["Yue"],"suffixes":[]}],"month":"December","year":"2022","keywords":"notion","pages":"11733–11751","bibtex":"@inproceedings{kwon_medjex_2022,\n\taddress = {Abu Dhabi, United Arab Emirates},\n\ttitle = {{MedJEx}: {A} {Medical} {Jargon} {Extraction} {Model} with {Wiki}'s {Hyperlink} {Span} and {Contextualized} {Masked} {Language} {Model} {Score}},\n\tshorttitle = {{MedJEx}},\n\turl = {https://aclanthology.org/2022.emnlp-main.805},\n\tdoi = {10.18653/v1/2022.emnlp-main.805},\n\tabstract = {This paper proposes a new natural language processing (NLP) application for identifying medical jargon terms potentially difficult for patients to comprehend from electronic health record (EHR) notes. We first present a novel and publicly available dataset with expert-annotated medical jargon terms from 18K+ EHR note sentences (MedJ). Then, we introduce a novel medical jargon extraction (MedJEx) model which has been shown to outperform existing state-of-the-art NLP models. First, MedJEx improved the overall performance when it was trained on an auxiliary Wikipedia hyperlink span dataset, where hyperlink spans provide additional Wikipedia articles to explain the spans (or terms), and then fine-tuned on the annotated MedJ data. Secondly, we found that a contextualized masked language model score was beneficial for detecting domain-specific unfamiliar jargon terms. Moreover, our results show that training on the auxiliary Wikipedia hyperlink span datasets improved six out of eight biomedical named entity recognition benchmark datasets. MedJEx is publicly available.},\n\turldate = {2024-01-03},\n\tbooktitle = {Proceedings of the 2022 {Conference} on {Empirical} {Methods} in {Natural} {Language} {Processing}},\n\tpublisher = {Association for Computational Linguistics},\n\tauthor = {Kwon, Sunjae and Yao, Zonghai and Jordan, Harmon and Levy, David and Corner, Brian and Yu, Hong},\n\teditor = {Goldberg, Yoav and Kozareva, Zornitsa and Zhang, Yue},\n\tmonth = dec,\n\tyear = {2022},\n\tkeywords = {notion},\n\tpages = {11733--11751},\n}\n\n\n\n","author_short":["Kwon, S.","Yao, Z.","Jordan, H.","Levy, D.","Corner, B.","Yu, H."],"editor_short":["Goldberg, Y.","Kozareva, Z.","Zhang, Y."],"key":"kwon_medjex_2022","id":"kwon_medjex_2022","bibbaseid":"kwon-yao-jordan-levy-corner-yu-medjexamedicaljargonextractionmodelwithwikishyperlinkspanandcontextualizedmaskedlanguagemodelscore-2022","role":"author","urls":{"Paper":"https://aclanthology.org/2022.emnlp-main.805"},"keyword":["notion"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/sarveshsoni","dataSources":["taWdMrienBzqHC2tC"],"keywords":["notion"],"search_terms":["medjex","medical","jargon","extraction","model","wiki","hyperlink","span","contextualized","masked","language","model","score","kwon","yao","jordan","levy","corner","yu"],"title":"MedJEx: A Medical Jargon Extraction Model with Wiki's Hyperlink Span and Contextualized Masked Language Model Score","year":2022}