%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 }