Hyperbolic Representation Learning for Fast and Efficient Neural Question Answering

Open paper
Benchmark Model Rank Results
question-answering-on-trecqaHyperQA#5MAP: 0.770MRR: 0.825
question-answering-on-wikiqaHyperQA#5MAP: 0.712MRR: 0.727

Rank counts only results with a code link.