Papers by Sichao Wu

Copied to clipboard

Challenge:	Recent studies have shown that few-shot relation classification models can be used to extract any relation of interest from a collection of text with only a few example instances.
Approach:	They propose to modify the training routine to encourage models to better discriminate between relations involving similar entity types.
Outcome:	The proposed models outperform human models on relation extraction tasks while relying on entity type information.