Add tweet_qa evaluator.

Marker-Inc-Korea / RAGchain

Extension of Langchain for RAG. Easy benchmarking, multiple retrievals, reranker, time-aware RAG, and so on...

Apache License 2.0

279 stars 27 forks source link

Closed minsing-jin closed 1 year ago

minsing-jin commented 1 year ago

Tweet QA performance is measured by calculating the BLEU-1/Meteor/ROUGE-L score. https://huggingface.co/datasets/tweet_qa#supported-tasks-and-leaderboards

minsing-jin commented 1 year ago

tweet_qa is not RAG