Skip to main content

Advertisement

Table 5 The performance of different matching models using character-level and word-level inputs

From: Applying deep matching networks to Chinese medical question answering: a study and a dataset

Input Unit Model P@1(%) MAP(%)
  Random 20.0 45.7
Char BM25 26.6 51.2
  multiCNN[17] 39.8 60.1
  MV-LSTM 58.1 74.5
  MatchPyramid 66.0 79.3
Word BM25 23.6 49.0
  multiCNN[17] 40.0 60.5
  MV-LSTM 59.3 75.3
  MatchPyramid 58.8 74.9