Just the urls, ma'am.


Postby Jonathan » Wed May 15, 2019 6:23 pm


SQuAD2.0 combines the 100,000 questions in SQuAD1.1 with over 50,000 new, unanswerable questions written adversarially by crowdworkers to look similar to answerable ones. To do well on SQuAD2.0, systems must not only answer questions when possible, but also determine when no answer is supported by the paragraph and abstain from answering. SQuAD2.0 is a challenging natural language understanding task for existing models, and we release SQuAD2.0 to the community as the successor to SQuAD1.1. We are optimistic that this new dataset will encourage the development of reading comprehension systems that know what they don't know.

BERT-derived models are beating the crowdworkers. I'd still like to see expert human performance up there.
Grand Pooh-Bah
Posts: 6421
Joined: Tue Sep 19, 2006 7:45 pm
Location: Portland, OR

Return to Links

Who is online

Users browsing this forum: No registered users and 2 guests