Enhancing the LexVec Distributed Word Representation Model Using Positional Contexts and External Memory · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1606.01283/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTEnhancing the LexVec Distributed Word Representation Model Using Positional Contexts and External Memory — mentioned by atrudeauhttps://news.ycombinator.com/item?id=13777720urn:hackerpapers:mention:1606.01283:13777720Thu, 02 Mar 2017 20:06:55 GMT<p>Google Analogy Task results ( detailed results at http://pastebin.com/PF96nMfX ): Semantic accuracy: 63.84 % Syntactic accuracy: 67.00 % Here performance is not great (great would be &gt;80% on semantic and &gt;70% on syntactic). As this task requires nearest neighbor lookups, performance is impacted by vocabulary size. Since models trained using Wikipedia alone usually limit vocabulary to something ~300k words, we can try that to get scores which are comparable to those posted by the GloVe [1] and LexVec [2] papers by only using the first 300k words in the pre-trained vectors, giving the following…</p><p><a href="https://hackerpaper.kaipfister.de/p/1606.01283/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL