Extracting topical phrases from clinical documents
Y. He. Thirtieth AAAI Conference on Artificial Intelligence, (марта 2016)
Аннотация
In clinical documents, medical terms are often expressed in multi-word phrases. Traditional topic modelling approaches relying on the "bag-of-words" assumption are not effective in extracting topic themes from clinical documents. This paper proposes to first extract medical phrases using an off-the-shelf tool for medical concept mention extraction, and then train a topic model which takes a hierarchy of Pitman-Yor processes as prior for modelling the generation of phrases of arbitrary length. Experimental results on patients' discharge summaries show that the proposed approach outperforms the state-of-the-art topical phrase extraction model on both perplexity and topic coherence measure and finds more interpretable topics.
Thirtieth AAAI Conference on Artificial Intelligence
год
2016
месяц
mar
file
Full Text PDF:C\:\\Users\\klaus\\Zotero\\storage\\H8A45APL\\He - 2016 - Extracting Topical Phrases from Clinical Documents.pdf:application/pdf;Snapshot:C\:\\Users\\klaus\\Zotero\\storage\\B68J3FHS\\11771.html:text/html
%0 Conference Paper
%1 he_extracting_2016
%A He, Yulan
%B Thirtieth AAAI Conference on Artificial Intelligence
%D 2016
%K terminologieextraktion
%T Extracting topical phrases from clinical documents
%U https://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/view/11771
%X In clinical documents, medical terms are often expressed in multi-word phrases. Traditional topic modelling approaches relying on the "bag-of-words" assumption are not effective in extracting topic themes from clinical documents. This paper proposes to first extract medical phrases using an off-the-shelf tool for medical concept mention extraction, and then train a topic model which takes a hierarchy of Pitman-Yor processes as prior for modelling the generation of phrases of arbitrary length. Experimental results on patients' discharge summaries show that the proposed approach outperforms the state-of-the-art topical phrase extraction model on both perplexity and topic coherence measure and finds more interpretable topics.
@inproceedings{he_extracting_2016,
abstract = {In clinical documents, medical terms are often expressed in multi-word phrases. Traditional topic modelling approaches relying on the "bag-of-words" assumption are not effective in extracting topic themes from clinical documents. This paper proposes to first extract medical phrases using an off-the-shelf tool for medical concept mention extraction, and then train a topic model which takes a hierarchy of Pitman-Yor processes as prior for modelling the generation of phrases of arbitrary length. Experimental results on patients' discharge summaries show that the proposed approach outperforms the state-of-the-art topical phrase extraction model on both perplexity and topic coherence measure and finds more interpretable topics.},
added-at = {2019-05-21T15:25:32.000+0200},
author = {He, Yulan},
biburl = {https://www.bibsonomy.org/bibtex/2cb1c597ceff651602bf41ad13cdb46bd/lepsky},
booktitle = {Thirtieth {AAAI} {Conference} on {Artificial} {Intelligence}},
file = {Full Text PDF:C\:\\Users\\klaus\\Zotero\\storage\\H8A45APL\\He - 2016 - Extracting Topical Phrases from Clinical Documents.pdf:application/pdf;Snapshot:C\:\\Users\\klaus\\Zotero\\storage\\B68J3FHS\\11771.html:text/html},
interhash = {67d344a0d34dfb1f5164fdda52f5fcaa},
intrahash = {cb1c597ceff651602bf41ad13cdb46bd},
keywords = {terminologieextraktion},
language = {en},
month = mar,
timestamp = {2019-05-21T15:25:32.000+0200},
title = {Extracting topical phrases from clinical documents},
url = {https://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/view/11771},
urldate = {2019-05-20},
year = 2016
}