Table 3 Results on 10661 sentences from MiPACQ corpus.
From: Parsing clinical text: how good are the state-of-the-art parsers?
Parser | Corpus | BR (%) | BP (%) | BF (%) |
|---|---|---|---|---|
Stanford | WSJ | 75.54 | 74.41 | 74.97 |
| Â | MiPACQ | 84.28 | 83.16 | 83.72 |
| Â | WSJ + MiPACQ | 84.30 | 84.00 | 84.15 |
Bikel | WSJ | 73.49 | 75.78 | 74.62 |
| Â | MiPACQ | 77.59 | 78.09 | 77.84 |
| Â | WSJ + MiPACQ | 77.43 | 78.63 | 78.03 |
Charniak | WSJ | 70.63 | 78.11 | 74.18 |
| Â | MiPACQ | 80.88 | 86.39 | 83.54 |
| Â | WSJ + MiPACQ | 80.65 | 86.76 | 83.59 |