Our new X account is live! Follow @wizwand_team for updates

Abstractive Summarization on CNN/DailyMail full length F-1 (test)

41.69ROUGE-1

DCA MLE+SEM+RL, mpgen, with-comm, with caa (m7)

Updated 3d ago

Evaluation Results

Method
DCA MLE+SEM+RL, mpgen, with-comm, with caa (m7) 2018.03	41.69	19.47	37.92	-
(m7) DCA MLE+SEM+RL, mpgen, with-comm, with caa 2018.03	41.69	19.47	37.92	-
abstract-RL 2018.08	41.16	15.75	39.08	-
RL, with intra-attention 2018.03	41.16	15.75	39.08	-
RL, with intra-attention 2018.03	41.16	15.75	39.08	-
DCA MLE+SEM, mpgen, with-comm, with caa (m6) 2018.03	41.11	18.21	36.03	-
(m6) DCA MLE+SEM, mpgen, with-comm, with caa 2018.03	41.11	18.21	36.03	-
LATENT 2018.08	41.05	18.77	37.54	-
EXTRACT 2018.08	40.62	18.45	37.14	-
LEAD3 2018.08	40.34	17.7	36.57	-
EXTRACT-CNN 2018.08	40.11	17.52	36.39	-
REFRESH 2018.08	40	18.2	36.6	-
abstract-ML+RL 2018.08	39.87	15.82	36.9	-
ML+RL, with intra-attention 2018.03	39.87	15.82	36.9	-
ML+RL, with intra-attention 2018.03	39.87	15.82	36.9	-
Two-Layer Baseline (Pointer+Coverage) + Entailment Generation 2018.05	39.84	17.63	36.54	18.61
Two-Layer Baseline (Pointer+Coverage) + Entailment Gen. + Question Gen. 2018.05	39.81	17.64	36.54	18.54
controlled summarization with fixed values 2018.03	39.75	17.29	36.54	-
controlled summarization with fixed values 2018.03	39.75	17.29	36.54	-
Two-Layer Baseline (Pointer+Coverage) + Question Generation 2018.05	39.73	17.59	36.48	18.33
SummaRuNNer 2018.08	39.6	16.2	35.3	-
SummaRuNNer 2018.03	39.6	16.2	35.3	-
SummaRuNNer 2018.03	39.6	16.2	35.3	-
Two-Layer Baseline (Pointer+Coverage) 2018.05	39.56	17.52	36.36	18.17
Pointer+Coverage 2018.05	39.53	17.28	36.38	18.72
pointer+coverage 2018.08	39.53	17.28	36.38	-
pointer generator + coverage 2018.03	39.53	17.28	36.38	-
pointer generator + coverage 2018.03	39.53	17.28	36.38	-
DCA MLE+SEM, mpgen, with-comm (m5) 2018.03	39.52	17.12	36.9	-
(m5) DCA MLE+SEM, mpgen, with-comm 2018.03	39.52	17.12	36.9	-
LEAD3 (Nallapati et al., 2017) 2018.08	39.2	15.7	35.5	-
Pointer+Coverage 2018.05	38.82	16.81	35.71	18.14
graph-based attention 2018.03	38.01	13.9	34	-
MLE+RL, pgen, no-comm (m3) 2018.03	38.01	16.43	35.49	-
graph-based attention 2018.03	38.01	13.9	34	-
(m3) MLE+RL, pgen, no-comm (baseline-3) 2018.03	38.01	16.43	35.49	-
DCA MLE+SEM, pgen, no-comm (m4) 2018.03	37.45	15.9	34.56	-
(m4) DCA MLE+SEM, pgen, no-comm 2018.03	37.45	15.9	34.56	-
MLE+SEM, pgen, no-comm (m2) 2018.03	36.9	15.02	33	-
(m2) MLE+SEM, pgen, no-comm (baseline-2) 2018.03	36.9	15.02	33	-
LATENT+COMPRESS 2018.08	36.69	15.43	34.33	-
Pointer 2018.05	36.44	15.66	33.42	15.35
pointer generator 2018.03	36.44	15.66	33.42	-
pointer generator 2018.03	36.44	15.66	33.42	-
MLE, pgen, no-comm (m1) 2018.03	36.12	14.38	33.83	-
(m1) MLE, pgen, no-comm (baseline-1) 2018.03	36.12	14.38	33.83	-
abstract 2018.08	35.46	13.3	32.65	-
Seq2Seq (50k vocab) 2018.05	31.33	11.81	28.83	12.03