Skip to main content
. Author manuscript; available in PMC: 2018 Nov 1.
Published in final edited form as: J Biomed Inform. 2017 Jun 15;75 Suppl:S129–S137. doi: 10.1016/j.jbi.2017.06.014

Table 3.

Experimental performance of nDCG for candidate psychiatric symptoms ranking by using sentence and phrase embeddings based sematic similarity. The employed corpora - psychiatric notes, psychiatric forum postings, and MIMICII - for embedding generation are integrated incrementally.

Method nDCG
Baseline Random 0.696
Dictionary 0.734
TF-IDF 0.745
Sentence embeddings model notes 0.741
+forum 0.784
+mimic 0.768
Phrase embeddings model notes 0.734
+forum 0.736
+mimic 0.728