Review Article
Applications of Natural Language Processing in Biodiversity Science
Table 3
Existing IE systems for biology [
17ā
26].
| System | Approach | Structure of Text | Knowledge in | Application domain | Reference |
| AkanePPI | shallow parsing | sentence-split, tokenized, and annotated | | protein interactions | [17] | EMPathIE | pattern matching | text | EMP database | enzymes | [18] | PASTA | pattern matching | text | biological lexicons | protein structure | [19] | BioIE | pattern matching | xml | dictionary of terms | biomedicine | [20] | BioRAT | pattern matching, sub-language driven | could be xml, html, text or asn.1, can do full-length pdf papers (converts to text) | dictionary for protein and gene names, dictionary for interactions, and synonyms; text pattern template | biomedicine | [21] | Chilibot | shallow parsing | not sure what was used in paper, but could be xml, html, text or asn.1 | nomenclature dictionary | biomedicine | [22] | Dragon Toolkit | mixed syntactic semantic | text | domain ontologies | genomics | [23] | EBIMed | pattern matching | xml | dictionary of terms | biomedicine | [24] | iProLINK | shallow parsing | text | protein name dictionary, ontology, and annotated corpora | proteins | [25] | LitMiner | mixed syntactic semantic | web documents | | Drosophila research | [26] |
|
|