Characterizing Diseases from Unstructured Text: A Vocabulary Driven Word2vec Approach

被引:18
作者
Ghosh, Saurav [1 ]
Chakraborty, Prithwish [1 ]
Cohn, Emily [2 ]
Brownstein, John S. [3 ]
Ramakrishnan, Naren [1 ]
机构
[1] Virginia Tech, Blacksburg, VA 24061 USA
[2] Boston Childrens Hosp, Boston, MA USA
[3] Harvard Med Sch, Boston, MA USA
来源
CIKM'16: PROCEEDINGS OF THE 2016 ACM CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT | 2016年
关键词
Disease characterization; Domain-specific word embeddings; word2vec; Dis2Vec; HealthMap;
D O I
10.1145/2983323.298336
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Traditional disease surveillance can be augmented with a wide variety of real-time sources such as, news and social media. However, these sources are in general unstructured and, construction of surveillance tools such as taxonomical correlations and trace mapping involves considerable human supervision. In this paper, we motivate a disease vocabulary driven word2vec model (Dis2Vec) to model diseases and constituent attributes as word embeddings from the HealthMap news corpus. We use these word embeddings to automatically create disease taxonomies and evaluate our model against corresponding human annotated taxonomies. We compare our model accuracies against several state-of-the art word2vec methods. Our results demonstrate that Dis2Vec outperforms traditional distributed vector representations in its ability to faithfully capture taxonomical attributes across different class of diseases such as endemic, emerging and rare.
引用
收藏
页码:1129 / 1138
页数:10
相关论文
共 22 条
  • [1] [Anonymous], 2013, P 2013 C N AM CHAPTE
  • [2] [Anonymous], 2013, CORR
  • [3] [Anonymous], 2009, Advances in neural information processing systems
  • [4] Baroni M, 2014, PROCEEDINGS OF THE 52ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1, P238
  • [5] Distributional Memory: A General Framework for Corpus-Based Semantics
    Baroni, Marco
    Lenci, Alessandro
    [J]. COMPUTATIONAL LINGUISTICS, 2010, 36 (04) : 673 - 721
  • [6] Bengio Y, 2006, STUD FUZZ SOFT COMP, V194, P137
  • [7] Collobert R., 2008, P 25 INT C MACH LEAR, P160, DOI [10.1145/1390156.1390177, DOI 10.1145/1390156.1390177]
  • [8] Collobert R, 2011, J MACH LEARN RES, V12, P2493
  • [9] Application of Pixel Intensity Based Medical Image Segmentation Using NSGA II Based OptiMUSIG Activation Function
    De, Sourav
    Bhattacharyya, Siddhartha
    Chakraborty, Susanta
    [J]. 2014 6TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND COMMUNICATION NETWORKS, 2014, : 262 - 267
  • [10] HealthMap: Global infectious disease monitoring through automated classification and visualization of Internet media reports
    Freifeld, Clark C.
    Mandl, Kenneth D.
    Ras, Ben Y.
    Bronwnstein, John S.
    [J]. JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION, 2008, 15 (02) : 150 - 157