Phonetics and Ambiguity Comprehension Gated Attention Network for Humor Recognition

Table 3

Experimental results on Oliners dataset. Best results are in bold. The results with superscript are imported from the literature [3, 12, 16, 17].

Models	Acc (%)	P (%)	R (%)	F1 (%)
SVM	83.12	88.04	80.26	82.24
HCFW2V	79.7	77.6	83.6	80.5
Syntactic	85.0	82.7	89.1	85.8
TM	70.5	72.1	66.7	69.3
CNN	84.24	85.73	86.46	86.09
CNN + HN + F	89.7	87.2	93.6	90.3
Bi-lstm + CNN	85.97	86.30	85.21	85.75
Bi-GRU	85.92	87.81	86.08	86.94
Bi-GRU+F	84.78	84.11	84.69	84.40
PACGA	89.47	88.78	91.84	90.28