Table 3.
List of boundary words
| Category | Word | AIMed | GENIA | GENETAG | ||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Na | Nn | Eb | Na | Nn | Eb | Na | Nn | Eb | ||
| Adjective | constitutive | 0 | 0 | 0.0000 | 12 | 11 | 0.9986 | 2 | 2 | 1.0000 |
| endogenous | 0 | 0 | 0.0000 | 22 | 11 | 0.9183 | 9 | 9 | 1.0000 | |
| exogenous | 0 | 0 | 0.0000 | 9 | 16 | 0.9427 | 2 | 3 | 0.9710 | |
| inducible | 0 | 0 | 0.0000 | 18 | 17 | 0.9994 | 0 | 0 | 0.0000 | |
| low | 0 | 0 | 0.0000 | 14 | 11 | 0.9896 | 2 | 3 | 0.9710 | |
| major | 0 | 0 | 0.0000 | 25 | 15 | 0.9544 | 1 | 5 | 0.6500 | |
| putative | 0 | 0 | 0.0000 | 15 | 15 | 1.0000 | 0 | 0 | 0.0000 | |
| recombinant | 1 | 8 | 0.5033 | 36 | 24 | 0.9710 | 26 | 2 | 0.3712 | |
| soluble | 1 | 10 | 0.4395 | 14 | 15 | 0.9991 | 1 | 4 | 0.7219 | |
| Noun before | factor | 0 | 0 | 0.0000 | 5 | 26 | 0.6374 | 17 | 15 | 0.9972 |
| plasma | 0 | 0 | 0.0000 | 13 | 1 | 0.3712 | 17 | 12 | 0.9784 | |
| protein | 12 | 34 | 0.8281 | 159 | 18 | 0.4743 | 53 | 10 | 0.6313 | |
| Noun after | form | 0 | 0 | 0.0000 | 21 | 14 | 0.9710 | 0 | 0 | 0.0000 |
| pathway | 0 | 0 | 0.0000 | 0 | 0 | 0.0000 | 8 | 10 | 0.9911 | |
| protein | 40 | 17 | 0.8791 | 794 | 14 | 0.1262 | 241 | 2 | 0.0688 | |
Here, "Noun before" indicates the noun occurring before an entity as a modifier, "Noun after" indicates the noun occurring after an entity as a head. Na represents the number of the annotated occurrences, and Nn represents the number of un-annotated occurrences.