https://hackerpaper.kaipfister.de/p/1507.05523/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=15548431urn:hackerpapers:mention:1507.05523:15548431Wed, 25 Oct 2017 08:37:45 GMT<p>Thank you Sebastian. Keep up the great work ! You will note that negative sampling improved by leveraging information on word pairs form dictionaries entries (we called it &quot;controlled negative sampling&quot;) do help, though not much. It actually really depends in the rare words rate (see section 5.4, improvement ranges from 0.7% up to 10%). But I guess it is already an interesting, somehow counter-intuitive, observation. Another very interesting observation is that you can also choose to just clamp a general purpose dataset and expand it with external contextual information (meaning not using is…</p><p><a href="https://hackerpaper.kaipfister.de/p/1507.05523/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL