Skip to main content

Advertisement

Table 7 Disjoint corpus ensemble results on clinical + medical development set

From: Synonym extraction and abbreviation expansion with ensembles of semantic spaces

 Strategy Normalize Abbr →Exp Exp →Abbr Syn
 Clinical  Medical  Clinical  Medical  Clinical  Medical
RI_4 RI_4 RI_4 RI_8 RI_20 RI_20
RP_4_sw RP_4_sw RP_4_sw RP_8_sw RP_4_sw RP_2_sw
AVG True 0.13 0.09 0.39
AVG False 0.24 0.11 0.39
SUM True 0.13 0.09 0.34
SUM False 0.32 0.17 0.52
AVG →AVG   0.15 0.09 0.41
SUM →SUM   0.13 0.07 0.40
AVG →SUM   0.15 0.09 0.41
SUM →AVG   0.13 0.07 0.40
  1. Results (P = weighted precision, R = recall, top ten) of the best models with and without post-processing on the three tasks. Dynamic # of suggestions allows the model to suggest less than ten terms in order to improve precision. The results are based on the application of the model combinations to the development data.