Hi, However, we suggest to do this NOT from parse trees obtained using a > grammar learned from supervised training or provided by hand-coding; > but rather from parse trees obtained via unsupervised learning. >
Ah, this is the bit I was missing. > Referring to > > https://arxiv.org/pdf/1401.3372.pdf > > I am suggesting word2vec style embedding as a tool to assist with the > "grouping" referred to in step 4 in the numbered list at the start of > section 5.1; i.e. in Step 2 of the numbered list occurring after the > bullet list in section 5.2.2, which reads > > "2. Cluster words into categories based on the similarity of their > associated usage links" > Got it, thanks. Cassio -- Cassio Pennachin -- You received this message because you are subscribed to the Google Groups "opencog" group. To unsubscribe from this group and stop receiving emails from it, send an email to opencog+unsubscr...@googlegroups.com. To post to this group, send email to opencog@googlegroups.com. Visit this group at https://groups.google.com/group/opencog. To view this discussion on the web visit https://groups.google.com/d/msgid/opencog/CADwLDSTAwTGHninLdkiExtd-kePKdi_3q2W99OveqkPRo5b1bg%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
