Leverage Label and Word Embedding for Semantic Sparse Web Service Discovery

Table 1

Performance of the proposed approach.

Query	LDA			Meta-LDA			Gaussian LDA			LNTM
	p	r	f	p	r	f	p	r	f	p	r	f
@10	0.64	0.30	0.40	0.78	0.41	0.54	0.76	0.37	0.50	0.91	0.46	0.61
@15	0.57	0.35	0.43	0.80	0.39	0.52	0.69	0.43	0.53	0.82	0.55	0.65
@20	0.50	0.38	0.44	0.74	0.42	0.53	0.61	0.47	0.53	0.75	0.58	0.65
@25	0.45	0.31	0.43	0.69	0.39	0.49	0.58	0.51	0.54	0.71	0.63	0.66
@30	0.41	0.44	0.43	0.63	0.49	0.55	0.55	0.54	0.54	0.69	0.67	0.67
@35	0.38	0.46	0.42	0.67	0.53	0.59	0.51	0.59	0.55	0.65	0.72	0.68
@40	0.36	0.49	0.42	0.61	0.59	0.60	0.49	0.61	0.54	0.63	0.73	0.67