https://hackerpaper.kaipfister.de/p/1511.04868/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=11912139urn:hackerpapers:mention:1511.04868:11912139Wed, 15 Jun 2016 21:05:40 GMT<p>Sure, there are a lot of potential things to do - either by enumerating towards the full &quot;brute force&quot; loss partway as I think you are hinting toward, or treating as a subsequences, or something else [0, 1, 2]. The point is, IMO RNNs do need some kind of structured loss (more than per step likelihood) to be competitive with HMM approaches using Viterbi decoding, in addition to some sequence smarts (such as beam search) in decoding. At least in NMT, enumerating the possible decisions as 3n + 1 is almost impossible since the softmax size is generally the memory bottleneck in training - and a…</p><p><a href="https://hackerpaper.kaipfister.de/p/1511.04868/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG