Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets — mentioned by patrick-lewis

Mon, 24 Aug 2020 11:54:12 GMT

Hi, first author here. Yes, we evaluated 3 retrieval-based models, DPR, RAG and FID - check out the paper for the numbers (https://arxiv.org/pdf/2008.02637.pdf)

Paper and discussion history. A mention is not an endorsement.

Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets — mentioned by ninjin

Mon, 24 Aug 2020 00:09:21 GMT

Second author here with a link to the arXiv paper: https://arxiv.org/abs/2008.02637 Although I have to say, VentureBeat did much better than most media outlets I have seen writing about current research and what they write is not only accurate but also largely devoid of hype. Perhaps we actually managed to “keep the hype down” as we intended when writing this piece? I will check in on this post now and then if you have questions and see if the first author is interested in joining when he wakes up as he really did all the legwork for this one.

Paper and discussion history. A mention is not an endorsement.

Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets · HackerPapers discussions

Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets — mentioned by patrick-lewis

Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets — mentioned by ninjin