Skip to Main Content
Table 1: 
Test results of models. “(2M)” / “(20M)” denotes using the corresponding number of automatically labeled Gigaword data instances as additional training data.
MethodsBLEU
PBMT (Pourdamghani et al., 2016) 26.9 
Tree2Str (Flanigan et al., 2016) 23.0 
TSP (Song et al., 2016) 22.4 
S2S+Anon (Konstas et al., 2017) 22.0 
GraphLSTM (Song et al., 2018) 23.3 
t-GCNSEQ (Damonte and Cohen, 2019) 23.9 
g-GCNSEQ (Damonte and Cohen, 2019) 24.4 
 
Transformer 17.7 
Graph Transformer 25.9 
 
S2S+Anon (2M) (Konstas et al., 2017) 32.3 
S2S+Anon (20M) (Konstas et al., 2017) 33.8 
S2S+Copy (2M) (Song et al., 2018) 31.7 
GraphLSTM (2M) (Song et al., 2018) 33.6 
 
Transformer (2M) 35.1 
Graph Transformer (2M) 36.4 
MethodsBLEU
PBMT (Pourdamghani et al., 2016) 26.9 
Tree2Str (Flanigan et al., 2016) 23.0 
TSP (Song et al., 2016) 22.4 
S2S+Anon (Konstas et al., 2017) 22.0 
GraphLSTM (Song et al., 2018) 23.3 
t-GCNSEQ (Damonte and Cohen, 2019) 23.9 
g-GCNSEQ (Damonte and Cohen, 2019) 24.4 
 
Transformer 17.7 
Graph Transformer 25.9 
 
S2S+Anon (2M) (Konstas et al., 2017) 32.3 
S2S+Anon (20M) (Konstas et al., 2017) 33.8 
S2S+Copy (2M) (Song et al., 2018) 31.7 
GraphLSTM (2M) (Song et al., 2018) 33.6 
 
Transformer (2M) 35.1 
Graph Transformer (2M) 36.4 
Close Modal

or Create an Account

Close Modal
Close Modal