Chemical Entity Recognition and Resolution to ChEBI

Table 2

Evaluation of entity recognition, subset of the gold standard composed by 9,696 chemical entities that contain a mapping to ChEBI. Results of entity identification (named entity recognition and resolution) for each alignment and method are shown in this table. The dictionary method recognized and mapped a total of 18,683 entities while the machine-learning method recognized and mapped 10,681 entities. True positives (TP) is the amount of entity recognitions that agree with the gold standard for each assessment. Values of precision, recall, and F-measure are presented.

Assessment	Method	TP	Precision	Recall	F-measure
Exact matching	Dictionary	5,651	30.25	58.28	38.83
	Machine learning	5,830	54.60	60.13	57.23
Left matching	Dictionary	5,913	31.65	60.98	41.67
	Machine learning	6,084	56.98	62.75	59.72
Right matching	Dictionary	6,158	32.96	63.51	43.40
	Machine learning	5,948	55.70	61.34	58.39
Left/right matching	Dictionary	6,435	34.44	66.37	45.35
	Machine learning	6,307	59.07	65.05	61.91
Partial matching	Dictionary	7,654	40.97	78.94	53.94
	Machine learning	6,703	62.78	69.13	65.80