Text-to-Text Pre-Training for Data-to-Text Tasks

21 May 2020Mihir Kale

We study the pre-train + fine-tune strategy for data-to-text tasks. Fine-tuning T5 achieves state-of-the-art results on the WebNLG, MultiWoz and ToTTo benchmarks... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Data-to-Text Generation MULTIWOZ 2.1 T5-Base BLEU 35.1 # 1
Data-to-Text Generation ToTTo T5-3B BLEU 49.5 # 1
PARENT 58.4 # 1
Data-to-Text Generation WebNLG T5-Large BLEU 0.639 # 2
Data-to-Text Generation WebNLG T5-3B BLEU 0.628 # 4
Data-to-Text Generation WebNLG T5-Small BLEU 0.626 # 5
Data-to-Text Generation WebNLG T5-Base BLEU 0.647 # 1
Data-to-Text Generation WebNLG Full T5-Large BLEU 57.1 # 2
Data-to-Text Generation WebNLG Full T5-3B BLEU 54 # 4
Data-to-Text Generation WebNLG Full T5-Small BLEU 52 # 7
Data-to-Text Generation WebNLG Full T5-Base BLEU 55.2 # 3

Methods used in the Paper