https://hackerpaper.kaipfister.de/p/1806.02847/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=18396257urn:hackerpapers:mention:1806.02847:18396257Wed, 07 Nov 2018 00:45:26 GMT<p>bert provides incremental improvements on tasks that don&#x27;t really stress-test contextualized world knowledge in linguistic tasks — contrast with Winograd schemas (SOTA: https://arxiv.org/pdf/1806.02847.pdf). Corpus data and compute don&#x27;t magically solve everything.</p><p><a href="https://hackerpaper.kaipfister.de/p/1806.02847/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.AIhttps://news.ycombinator.com/item?id=17291034urn:hackerpapers:mention:1806.02847:17291034Tue, 12 Jun 2018 06:01:58 GMT<p>Also notable this week is https://arxiv.org/abs/1806.02847 from Google where they got an 11% improvement on Winograd schema performance using a similar idea.</p><p><a href="https://hackerpaper.kaipfister.de/p/1806.02847/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.AI