Stop Incorrect Comparisons in End-to-End Relation Extraction

Taillé et al at EMNLP 2020 — what are we measuring, what are we comparing to, what’s not explicated.

Stop incorrect comparisons in end-to-end RE. Image: LinkedIn.

Bruno Taillé, Vincent Guigue, Geoffrey Scoutheeten and patrick gallinari asked these important questions:

• What are we measuring?
• What are we comparing to?
• What are not explicated in the literature?

We should have more papers like this!

Let’s Stop Incorrect Comparisons in End-to-end Relation Extraction! https://arxiv.org/abs/2009.10684

Originally posted on LinkedIn.