E2E (End-to-End NLG Challenge)

Introduced by Novikova et al. in The E2E Dataset: New Challenges For End-to-End Generation

End-to-End NLG Challenge (E2E) aims to assess whether recent end-to-end NLG systems can generate more complex output by learning from datasets containing higher lexical richness, syntactic complexity and diverse discourse phenomena.

Source: Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Data-to-Text Generation	E2E NLG Challenge	S_1^R
Data-to-Text Generation	Cleaned E2E NLG Challenge	Control Prefixes
Table-to-Text Generation	E2E	HTLM
Data-to-Text Generation	E2E	self-mem + new data