Multilingual Negation Scope Resolution for Clinical Text

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Standard

Multilingual Negation Scope Resolution for Clinical Text. / lwp876, lwp876; Søgaard, Anders.

Proceedings of the 12th International Workshop on Health Text Mining and Information Analysis. Association for Computational Linguistics, 2022. p. 7–18.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Harvard

lwp876, L & Søgaard, A 2022, Multilingual Negation Scope Resolution for Clinical Text. in Proceedings of the 12th International Workshop on Health Text Mining and Information Analysis. Association for Computational Linguistics, pp. 7–18, 12th International Workshop on Health Text Mining and Information Analysis, Online, 19/04/2021.

APA

lwp876, L., & Søgaard, A. (2022). Multilingual Negation Scope Resolution for Clinical Text. In Proceedings of the 12th International Workshop on Health Text Mining and Information Analysis (pp. 7–18). Association for Computational Linguistics.

Vancouver

lwp876 L, Søgaard A. Multilingual Negation Scope Resolution for Clinical Text. In Proceedings of the 12th International Workshop on Health Text Mining and Information Analysis. Association for Computational Linguistics. 2022. p. 7–18

Author

lwp876, lwp876 ; Søgaard, Anders. / Multilingual Negation Scope Resolution for Clinical Text. Proceedings of the 12th International Workshop on Health Text Mining and Information Analysis. Association for Computational Linguistics, 2022. pp. 7–18

Bibtex

@inproceedings{ce021dfd262f42af96aeb7d2c6a50eed,
title = "Multilingual Negation Scope Resolution for Clinical Text",
abstract = "Negation scope resolution is key to high-quality information extraction from clinical texts, but so far, efforts to make encoders used for information extraction negation-aware have been limited to English. We present a universal approach to multilingual negation scope resolution, that overcomes the lack of training data by relying on disparate resources in different languages and domains. We evaluate two approaches to learn from these resources, training on combined data and training in a multi-task learning setup. Our experiments show that zero-shot scope resolution in clinical text is possible, and that combining available resources improves performance in most cases.",
author = "lwp876 lwp876 and Anders S{\o}gaard",
year = "2022",
language = "English",
pages = "7–18",
booktitle = "Proceedings of the 12th International Workshop on Health Text Mining and Information Analysis",
publisher = "Association for Computational Linguistics",
note = " 12th International Workshop on Health Text Mining and Information Analysis ; Conference date: 19-04-2021 Through 19-04-2021",

}

RIS

TY - GEN

T1 - Multilingual Negation Scope Resolution for Clinical Text

AU - lwp876, lwp876

AU - Søgaard, Anders

PY - 2022

Y1 - 2022

N2 - Negation scope resolution is key to high-quality information extraction from clinical texts, but so far, efforts to make encoders used for information extraction negation-aware have been limited to English. We present a universal approach to multilingual negation scope resolution, that overcomes the lack of training data by relying on disparate resources in different languages and domains. We evaluate two approaches to learn from these resources, training on combined data and training in a multi-task learning setup. Our experiments show that zero-shot scope resolution in clinical text is possible, and that combining available resources improves performance in most cases.

AB - Negation scope resolution is key to high-quality information extraction from clinical texts, but so far, efforts to make encoders used for information extraction negation-aware have been limited to English. We present a universal approach to multilingual negation scope resolution, that overcomes the lack of training data by relying on disparate resources in different languages and domains. We evaluate two approaches to learn from these resources, training on combined data and training in a multi-task learning setup. Our experiments show that zero-shot scope resolution in clinical text is possible, and that combining available resources improves performance in most cases.

M3 - Article in proceedings

SP - 7

EP - 18

BT - Proceedings of the 12th International Workshop on Health Text Mining and Information Analysis

PB - Association for Computational Linguistics

T2 - 12th International Workshop on Health Text Mining and Information Analysis

Y2 - 19 April 2021 through 19 April 2021

ER -

ID: 300450254