Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1906.01603/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTDo Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study — mentioned by terminalhealthhttps://news.ycombinator.com/item?id=20130855urn:hackerpapers:mention:1906.01603:20130855Sat, 08 Jun 2019 05:47:05 GMT<p>Indeed. Here is a very fresh paper finding that attention is certainly not all you need as sometimes recurrence is necessary. https://arxiv.org/abs/1906.01603 This is also obvious: Without recurrence you cannot remember information that is not externally visible, but it may be computationally very convenient and often necessary to maintain information that is hidden. The hard part is learning reps for hidden information as recurrences are plagued by vanishing and shattering gradients.</p><p><a href="https://hackerpaper.kaipfister.de/p/1906.01603/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL