Table 5.

Example of processed training data. Where each row corresponds to a word from the collection of abstracts in the training data. The Part of Speech column (POS) tag tokens as a common noun (NN), adjective (JJ), etc. The sentence ID column identifies a training example (i.e., all tokens with the same Sentence ID are inserted into the model as one training example. The label column describes whether a token is a software tool (T) or not (O).

Token	POS	Sentence ID	Label
MetaComp	NN	1.0	T
comprehensive	JJ	1.0	O
analysis	NN	1.0	O
software	NN	1.0	O
comparative	JJ	1.0	O