%0 Conference Paper %1 devine2014medical %A De Vine, Lance %A Zuccon, Guido %A Koopman, Bevan %A Sitbon, Laurianne %A Bruza, Peter %B Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management %C New York, NY, USA %D 2014 %I ACM %K lm medical semantic similarity %P 1819--1822 %R 10.1145/2661829.2661974 %T Medical Semantic Similarity with a Neural Language Model %U http://doi.acm.org/10.1145/2661829.2661974 %X Advances in neural network language models have demonstrated that these models can effectively learn representations of words meaning. In this paper, we explore a variation of neural language models that can learn on concepts taken from structured ontologies and extracted from free-text, rather than directly from terms in free-text. This model is employed for the task of measuring semantic similarity between medical concepts, a task that is central to a number of techniques in medical informatics and information retrieval. The model is built with two medical corpora (journal abstracts and patient records) and empirically validated on two ground-truth datasets of human-judged concept pairs assessed by medical professionals. Empirically, our approach correlates closely with expert human assessors (≈0.9) and outperforms a number of state-of-the-art benchmarks for medical semantic similarity. The demonstrated superiority of this model for providing an effective semantic similarity measure is promising in that this may translate into effectiveness gains for techniques in medical information retrieval and medical informatics (e.g., query expansion and literature-based discovery). %@ 978-1-4503-2598-1

@inproceedings{devine2014medical, abstract = {Advances in neural network language models have demonstrated that these models can effectively learn representations of words meaning. In this paper, we explore a variation of neural language models that can learn on concepts taken from structured ontologies and extracted from free-text, rather than directly from terms in free-text. This model is employed for the task of measuring semantic similarity between medical concepts, a task that is central to a number of techniques in medical informatics and information retrieval. The model is built with two medical corpora (journal abstracts and patient records) and empirically validated on two ground-truth datasets of human-judged concept pairs assessed by medical professionals. Empirically, our approach correlates closely with expert human assessors (≈0.9) and outperforms a number of state-of-the-art benchmarks for medical semantic similarity. The demonstrated superiority of this model for providing an effective semantic similarity measure is promising in that this may translate into effectiveness gains for techniques in medical information retrieval and medical informatics (e.g., query expansion and literature-based discovery).}, acmid = {2661974}, added-at = {2019-06-05T22:02:03.000+0200}, address = {New York, NY, USA}, author = {De Vine, Lance and Zuccon, Guido and Koopman, Bevan and Sitbon, Laurianne and Bruza, Peter}, biburl = {https://www.bibsonomy.org/bibtex/2d1619b2d60599a00be0b60ddb6251f8b/nosebrain}, booktitle = {Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management}, description = {Medical Semantic Similarity with a Neural Language Model}, doi = {10.1145/2661829.2661974}, interhash = {93fb5e4df011945ff57866358ed8f658}, intrahash = {d1619b2d60599a00be0b60ddb6251f8b}, isbn = {978-1-4503-2598-1}, keywords = {lm medical semantic similarity}, location = {Shanghai, China}, numpages = {4}, pages = {1819--1822}, publisher = {ACM}, series = {CIKM '14}, timestamp = {2019-06-05T22:02:03.000+0200}, title = {Medical Semantic Similarity with a Neural Language Model}, url = {http://doi.acm.org/10.1145/2661829.2661974}, year = 2014 }