Few-Shot-Table-to-Text-Generation
Few-Shot-Table-to-Text-Generation copied to clipboard
[EMNLP'21] Few-Shot Table-to-Text Generation with Prototype Memory
Results
2
Few-Shot-Table-to-Text-Generation issues
Sort by
recently updated
recently updated
newest added
In Figure2. when n is small (i.e., n ≤ 3), the model performances are relatively the same. where is prototypes result file? where is train_top_20_rerank_context.txt used?
As you have mentioned that you have used a Lucene based IR system and that would result in extracting the entire body of the wiki page containing the query i.e....