Table 2.
| a: Results for individual relations on the BIDMC corpus. P stands for precision, R stands for recall, and F1 stands for F-measure. Bold indicates statistically significant difference from corresponding F1 of the tokens-in-concepts baseline. Italic indicates significant difference from the corresponding F1 of the tokens-in-sentence baseline. | |||||||||
|---|---|---|---|---|---|---|---|---|---|
| BIDMC corpus | |||||||||
| P | R | F1 | P | R | F1 | P | R | F1 | |
| Tokens-in-concepts baseline | Tokens-in-sentence baseline | Semantic relation classifier | |||||||
| Relation | Present disease–treatment relation type | ||||||||
| None | 0.65 | 0.75 | 0.69 | 0.70 | 0.74 | 0.72 | 0.84 | 0.86 | 0.85 |
| TADP | 0.60 | 0.57 | 0.58 | 0.61 | 0.66 | 0.63 | 0.76 | 0.83 | 0.79 |
| TXDP | 0.75 | 0.43 | 0.55 | 0.40 | 0.29 | 0.33 | 0.89 | 0.57 | 0.70 |
| TNDP | 0.89 | 0.73 | 0.80 | 0.63 | 0.45 | 0.53 | 1.00 | 0.73 | 0.84 |
| TCDP | 1.00 | 0.30 | 0.46 | 1.00 | 0.30 | 0.46 | 0.75 | 0.40 | 0.52 |
| TDDP | 0.50 | 0.20 | 0.29 | 0.75 | 0.40 | 0.52 | 0.75 | 0.30 | 0.43 |
| Possible disease–treatment relation type | |||||||||
| None | 0.72 | 0.79 | 0.75 | 0.78 | 0.88 | 0.83 | 0.76 | 0.85 | 0.80 |
| TAD | 0.60 | 0.71 | 0.65 | 0.78 | 0.82 | 0.80 | 0.78 | 0.82 | 0.80 |
| TCD | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| TDD | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| Present symptom–treatment relation type | |||||||||
| None | 0.71 | 0.83 | 0.76 | 0.80 | 0.84 | 0.82 | 0.87 | 0.89 | 0.88 |
| TASP | 0.35 | 0.29 | 0.32 | 0.39 | 0.47 | 0.43 | 0.64 | 0.76 | 0.70 |
| TXSP | 0.59 | 0.50 | 0.54 | 0.83 | 0.75 | 0.79 | 0.88 | 0.75 | 0.81 |
| TNSP | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| TCSP | 0.71 | 0.63 | 0.67 | 1.00 | 0.75 | 0.86 | 1.00 | 0.75 | 0.86 |
| TDSP | 0.50 | 0.33 | 0.40 | 1.00 | 0.17 | 0.29 | 0.50 | 0.50 | 0.50 |
| Possible symptom–treatment relation type | |||||||||
| None | 0.81 | 0.92 | 0.86 | 0.91 | 0.97 | 0.94 | 0.99 | 0.97 | 0.98 |
| TAS | 0.46 | 0.27 | 0.34 | 0.82 | 0.64 | 0.72 | 0.87 | 0.91 | 0.89 |
| TCS | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| TDS | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| Disease–test relation type | |||||||||
| None | 0.84 | 0.84 | 0.84 | 0.73 | 0.77 | 0.75 | 0.89 | 0.90 | 0.90 |
| TRD | 0.82 | 0.82 | 0.82 | 0.72 | 0.71 | 0.71 | 0.88 | 0.91 | 0.89 |
| TID | 0.38 | 0.34 | 0.36 | 0.68 | 0.49 | 0.57 | 0.78 | 0.51 | 0.62 |
| Disease–symptom relation type | |||||||||
| None | 0.94 | 0.99 | 0.96 | 0.96 | 0.98 | 0.97 | 0.97 | 0.99 | 0.98 |
| SSD | 0.88 | 0.78 | 0.82 | 0.63 | 0.56 | 0.59 | 0.88 | 0.78 | 0.82 |
| DCS | 0.60 | 0.23 | 0.33 | 0.82 | 0.69 | 0.75 | 0.89 | 0.62 | 0.73 |
| b: Results on individual relations on Partners corpus. P stands for precision, R stands for recall, and F1 stands for F-measure. Bold indicates statistically significant difference from corresponding F1 of the tokens-in-concepts baseline. Italic indicates significant difference from the corresponding F1 of the tokens-in-sentence baseline. | |||||||||
|---|---|---|---|---|---|---|---|---|---|
| Partners corpus | |||||||||
| P | R | F1 | P | R | F1 | P | R | F1 | |
| Tokens-in-concepts baseline | Tokens-in-sentence baseline | Semantic relation classifier | |||||||
| Relation | Present disease–treatment relation type | ||||||||
| None | 0.71 | 0.69 | 0.70 | 0.76 | 0.80 | 0.78 | 0.81 | 0.80 | 0.81 |
| TADP | 0.69 | 0.77 | 0.73 | 0.76 | 0.78 | 0.77 | 0.77 | 0.84 | 0.81 |
| TXDP | 0.00 | 0.00 | 0.00 | 0.67 | 0.29 | 0.40 | 0.00 | 0.00 | 0.00 |
| TNDP | 0.62 | 0.29 | 0.39 | 0.69 | 0.39 | 0.50 | 0.86 | 0.43 | 0.57 |
| TCDP | 0.67 | 0.53 | 0.59 | 0.66 | 0.56 | 0.61 | 0.75 | 0.54 | 0.63 |
| TDDP | 0.20 | 0.09 | 0.13 | 0.36 | 0.18 | 0.24 | 0.73 | 0.63 | 0.68 |
| Possible disease–treatment relation type | |||||||||
| None | 0.59 | 0.57 | 0.58 | 0.69 | 0.64 | 0.67 | 0.86 | 0.68 | 0.76 |
| TAD | 0.66 | 0.68 | 0.67 | 0.67 | 0.75 | 0.71 | 0.72 | 0.90 | 0.80 |
| TCD | 0.67 | 0.40 | 0.50 | 0.00 | 0.00 | 0.00 | 0.50 | 0.20 | 0.29 |
| TDD | 0.58 | 0.70 | 0.64 | 0.70 | 0.70 | 0.70 | 0.78 | 0.70 | 0.74 |
| Present symptom–treatment relation type | |||||||||
| None | 0.61 | 0.70 | 0.65 | 0.68 | 0.71 | 0.70 | 0.72 | 0.77 | 0.74 |
| TASP | 0.60 | 0.57 | 0.58 | 0.59 | 0.62 | 0.61 | 0.67 | 0.73 | 0.70 |
| TXSP | 0.20 | 0.07 | 0.11 | 0.22 | 0.07 | 0.11 | 0.33 | 0.11 | 0.16 |
| TNSP | 0.54 | 0.45 | 0.49 | 0.65 | 0.68 | 0.67 | 0.77 | 0.66 | 0.71 |
| TCSP | 0.54 | 0.56 | 0.55 | 0.56 | 0.59 | 0.58 | 0.60 | 0.59 | 0.59 |
| TDSP | 0.47 | 0.31 | 0.38 | 0.40 | 0.14 | 0.21 | 0.75 | 0.41 | 0.53 |
| Possible symptom–treatment relation type | |||||||||
| None | 0.81 | 0.94 | 0.87 | 0.84 | 0.93 | 0.88 | 0.94 | 0.96 | 0.95 |
| TAS | 0.48 | 0.23 | 0.32 | 0.43 | 0.25 | 0.32 | 0.77 | 0.75 | 0.76 |
| TCS | 0.71 | 0.34 | 0.47 | 0.72 | 0.62 | 0.67 | 0.89 | 0.86 | 0.88 |
| TDS | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| Disease–test relation type | |||||||||
| None | 0.64 | 0.69 | 0.66 | 0.63 | 0.69 | 0.66 | 0.73 | 0.75 | 0.74 |
| TRD | 0.78 | 0.80 | 0.79 | 0.79 | 0.81 | 0.80 | 0.84 | 0.86 | 0.85 |
| TID | 0.41 | 0.28 | 0.33 | 0.59 | 0.43 | 0.49 | 0.63 | 0.52 | 0.57 |
| Disease–symptom relation type | |||||||||
| None | 0.66 | 0.75 | 0.70 | 0.76 | 0.79 | 0.78 | 0.78 | 0.81 | 0.79 |
| SSD | 0.57 | 0.49 | 0.52 | 0.64 | 0.65 | 0.65 | 0.62 | 0.62 | 0.62 |
| DCS | 0.51 | 0.43 | 0.47 | 0.57 | 0.51 | 0.54 | 0.58 | 0.53 | 0.55 |