Table-to-text generation on DART benchmark leaderboard · SOTA2 Research

Table-to-text generation on DART

0.3928METEORTeacher

Evaluation Results

Method	Links
Teacher2023.07		0.3928	—	0.4545	0.6817	0.8304	0.4056	0.4856
FINE-TUNE2021.01		0.39	0.462	0.46	0.5	0.94	0.39	—
FINE-TUNE2021.01		0.39	0.47	0.46	0.51	0.94	0.4	—
Prefix2021.01		0.39	0.467	0.45	0.51	0.94	0.4	—
Fine-tune2021.10		0.39	0.46	0.46	—	—	—	—
LoRA2021.10		0.39	0.475	0.45	—	—	—	—
DSEE2021.10		0.39	0.475	0.46	—	—	—	—
GPT-2MEDIUM2021.07		0.39	0.462	0.46	0.5	0.94	0.39	—
GPT-2LARGE2021.07		0.39	0.47	0.46	0.51	0.94	0.4	—
HTLM2021.07		0.39	0.472	0.44	0.51	0.94	0.4	—
GPT-2LARGE2021.07		0.39	0.467	0.45	0.51	0.94	0.4	—
HTLM2021.07		0.39	0.471	0.45	0.5	0.94	0.39	—
ADAPTER (3%)2021.01		0.38	0.452	0.46	0.5	0.94	0.39	—
PREFIX (0.1%)2021.01		0.38	0.464	0.46	0.5	0.94	0.39	—
Adapters2021.10		0.38	0.454	0.46	—	—	—	—
Prefix2021.10		0.38	0.457	0.46	—	—	—	—
GPT-2MEDIUM2021.07		0.38	0.464	0.46	0.5	0.94	0.39	—
TVD2023.07		0.3788	—	0.4635	0.6736	0.8208	0.3717	0.4695
JS2023.07		0.3775	—	0.465	0.673	0.8193	0.3681	0.4685
KL2023.07		0.3745	—	0.4689	0.6707	0.816	0.3531	0.4624
RKL2023.07		0.3735	—	0.4791	0.6702	0.8141	0.3508	0.4563
SeqKD2023.07		0.3717	—	0.4749	0.6665	0.8115	0.3288	0.4554
DSEE2021.10		0.37	0.434	0.51	—	—	—	—
Pre-distill2023.07		0.3699	—	0.471	0.6675	0.8139	0.3408	0.456
ENGINE2023.07		0.3651	—	0.5063	0.662	0.8018	0.3094	0.444
ADAPTER (0.1%)2021.01		0.36	0.424	0.48	0.47	0.94	0.33	—
Non-distill (MLE)2023.07		0.3571	—	0.4997	0.6565	0.7976	0.291	0.4312
FT-TOP22021.01		0.34	0.41	0.56	0.43	0.93	0.21	—
FT-Top22021.10		0.34	0.381	0.56	—	—	—	—
HTLM2021.07		0.12	0.221	0.91	0.25	0.78	0.22	—