Expanding a dictionary of marker words for uncertainty and negation using distributional semantics
(2015) 6th International Workshop on Health Text Mining and Information Analysis, LOUHI 2015, co-located with EMNLP 2015 p.90-96- Abstract
Approaches to determining the factuality of diagnoses and findings in clinical text tend to rely on dictionaries of marker words for uncertainty and negation. Here, a method for semi-automatically expanding a dictionary of marker words using distributional semantics is presented and evaluated. It is shown that ranking candidates for inclusion according to their proximity to cluster centroids of semantically similar seed words is more successful than ranking them according to proximity to each individual seed word.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/7763505
- author
- Alfalahi, Alyaa ; Skeppstedt, Maira ; Ahlblom, Rickard ; Baskalayci, Roza ; Henriksson, Aron ; Asker, Lars ; Paradis, Carita LU and Kerren, Andreas
- organization
- publishing date
- 2015
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- clinical text, negation, uncertainty, marker words, distributional semantics
- host publication
- EMNLP 2015 - 6th International Workshop on Health Text Mining and Information Analysis, LOUHI 2015 : Proceedings of the Workshop - Proceedings of the Workshop
- editor
- Grouin, Cyril ; Hamon, Thierry ; Névéol, Aurélie and Zweigenbaum, Pierre
- pages
- 7 pages
- publisher
- The Association for Computational Linguistics
- conference name
- 6th International Workshop on Health Text Mining and Information Analysis, LOUHI 2015, co-located with EMNLP 2015
- conference location
- Lisbon, Portugal
- conference dates
- 2015-09-17
- external identifiers
-
- other:urn:nbn:se:lnu:diva-45648
- other:oai:DiVA.org:lnu-45648
- scopus:84992040738
- ISBN
- 9781941643327
- project
- StaViCTA - Advances in the description and explanation of stance in discourse using visual and computational text analytics
- language
- English
- LU publication?
- yes
- additional info
- Funding Information: This work was partly funded through the project StaViCTA by the framework grant “the Digitized Society Past, Present, and Future” with No. 2012-5659 from the Swedish Research Council (Veten-skapsrådet) and partly by the Swedish Foundation for Strategic Research through the project High-Performance Data Mining for Drug Effect Detection (ref. no. IIS11-0053) at Stockholm University, Sweden. The authors would also like to direct thanks to the reviewers for valuable comments. Publisher Copyright: © 2015 Association for Computational Linguistics.
- id
- ca58d1c4-4bfa-4f8a-9c4f-9e8291f1ce59 (old id 7763505)
- date added to LUP
- 2016-04-04 13:03:35
- date last changed
- 2022-04-22 20:31:08
@inproceedings{ca58d1c4-4bfa-4f8a-9c4f-9e8291f1ce59, abstract = {{<p>Approaches to determining the factuality of diagnoses and findings in clinical text tend to rely on dictionaries of marker words for uncertainty and negation. Here, a method for semi-automatically expanding a dictionary of marker words using distributional semantics is presented and evaluated. It is shown that ranking candidates for inclusion according to their proximity to cluster centroids of semantically similar seed words is more successful than ranking them according to proximity to each individual seed word.</p>}}, author = {{Alfalahi, Alyaa and Skeppstedt, Maira and Ahlblom, Rickard and Baskalayci, Roza and Henriksson, Aron and Asker, Lars and Paradis, Carita and Kerren, Andreas}}, booktitle = {{EMNLP 2015 - 6th International Workshop on Health Text Mining and Information Analysis, LOUHI 2015 : Proceedings of the Workshop}}, editor = {{Grouin, Cyril and Hamon, Thierry and Névéol, Aurélie and Zweigenbaum, Pierre}}, isbn = {{9781941643327}}, keywords = {{clinical text; negation; uncertainty; marker words; distributional semantics}}, language = {{eng}}, pages = {{90--96}}, publisher = {{The Association for Computational Linguistics}}, title = {{Expanding a dictionary of marker words for uncertainty and negation using distributional semantics}}, url = {{https://lup.lub.lu.se/search/files/6044942/7869308.pdf}}, year = {{2015}}, }