论文信息 - NECLA at the Medical Natural Language Processing Pilot Task (MedNLP)

NECLA at the Medical Natural Language Processing Pilot Task (MedNLP)

This paper gives an overview of NECLA’s submitted systems for the De-Identification and Complaint & Diagnosis subtasks of the Medical Natural Language Processing Pilot Task (MedNLP)[5]. Our systems combine features derived from Part of Speech (POS) tags, a domain-specific dictionary, the Unified Medical Language System (UMLS) metathesaurus and semantic network, and a small set of heuristics based on trigger-words and polarity propagation through sentence dependency parse trees.

Christopher Malon | Pierre-François Laquerre | Christopher Malon | P. Laquerre

[1] Masaru Kitsuregawa,et al. Polynomial to Linear: Efficient Classification with Conjunctive Features , 2009, EMNLP.

[2] Masaru Kitsuregawa,et al. Kernel Slicing: Scalable Online Training with Conjunctive Features , 2010, COLING.

[3] Andrew McCallum,et al. Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[4] Tomoko Ohkuma,et al. Overview of the NTCIR-10 MedNLP Task , 2013, NTCIR.

[5] Alan R. Aronson,et al. Effective mapping of biomedical text to the UMLS Metathesaurus: the MetaMap program , 2001, AMIA.

[6] Proceedings of the 10th NTCIR Conference on Evaluation of Information Access Technologies, NTCIR-10, National Center of Sciences, Tokyo, Japan, June 18-21, 2013 , 2013, NTCIR.