questions about evaluation

[hlee-top]

Regarding the accuracy of calculating the trigger word, why is it correct to only calculate the B-Tags and i-Tags separately, and not to parse the BIO tags?
Looking forward for your response, thank you！

EMNLP2018-JMEE/enet/testing.py

Lines 8 to 23 in 494451d

	def calculate_report(self, y, y_, transform=True):
	'''
	calculating F1, P, R
	:param y: golden label, list
	:param y_: model output, list
	:return:
	'''
	if transform:
	for i in range(len(y)):
	for j in range(len(y[i])):
	y[i][j] = self.voc_i2s[y[i][j]]
	for i in range(len(y_)):
	for j in range(len(y_[i])):
	y_[i][j] = self.voc_i2s[y_[i][j]]
	return precision_score(y, y_), recall_score(y, y_), f1_score(y, y_)