That makes sense as a starting point, indeed... BTW, Man Hin's earlier experimentation with word2vec code indicated that a very large amount of training data is probably needed to get meaningful results...
ben On Thu, Mar 30, 2017 at 10:43 PM, MB <[email protected]> wrote: > Hi Ben, > > I've been looking at the skip-gram model implementation for the contender > project. Tensorflow seem to have done something on that and it works quite > well. https://www.tensorflow.org/tutorials/word2vec . Maybe this could be a > good starting point > > Masresha > > On Mon, Mar 27, 2017 at 6:11 PM, Ben Goertzel <[email protected]> wrote: >> >> On Mon, Mar 27, 2017 at 10:12 AM, Ben Goertzel <[email protected]> wrote: >> > Now, the distinction between word2vec and sense2vec may indeed be >> > relevant here, because a word may be meaningfully be placed into two >> > categories at this stage (i.e. word sense disambiguation). So we may >> > want to do something like they describe in this paper >> > >> > >> > https://pdfs.semanticscholar.org/142f/38642629b9d268999ad876af482177d36697.pdf >> > >> > which is similar to sense2vec but slower to run, but has the advantage >> > of (unlike sense2vec) not requiring labeled training examples >> >> Code corresponding to the above paper is here: >> >> https://github.com/ninjin/huang_et_al_2012 >> >> A simpler, faster (but maybe worse) approach to the same problem is >> embodied in this code >> >> https://github.com/nishantrai18/cs671project >> >> The latter simpler code would be "easy" to apply to the current >> context, because it's based on postprocessing word2vec vectors, so I >> suppose one could apply it to postprocessing word2vec-type vectors >> obtained from "disjunct vectors" that are produced from ensembles of >> parse trees... >> >> -- Ben >> >> >> >> -- >> Ben Goertzel, PhD >> http://goertzel.org >> >> “Our first mothers and fathers … were endowed with intelligence; they >> saw and instantly they could see far … they succeeded in knowing all >> that there is in the world. When they looked, instantly they saw all >> around them, and they contemplated in turn the arch of heaven and the >> round face of the earth. … Great was their wisdom …. They were able to >> know all.... >> >> But the Creator and the Maker did not hear this with pleasure. … ‘Are >> they not by nature simple creatures of our making? Must they also be >> gods? … What if they do not reproduce and multiply?’ >> >> Then the Heart of Heaven blew mist into their eyes, which clouded >> their sight as when a mirror is breathed upon. Their eyes were covered >> and they could see only what was close, only that was clear to them.” >> >> — Popol Vuh (holy book of the ancient Mayas) > > -- Ben Goertzel, PhD http://goertzel.org “Our first mothers and fathers … were endowed with intelligence; they saw and instantly they could see far … they succeeded in knowing all that there is in the world. When they looked, instantly they saw all around them, and they contemplated in turn the arch of heaven and the round face of the earth. … Great was their wisdom …. They were able to know all.... But the Creator and the Maker did not hear this with pleasure. … ‘Are they not by nature simple creatures of our making? Must they also be gods? … What if they do not reproduce and multiply?’ Then the Heart of Heaven blew mist into their eyes, which clouded their sight as when a mirror is breathed upon. Their eyes were covered and they could see only what was close, only that was clear to them.” — Popol Vuh (holy book of the ancient Mayas) -- 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 [email protected]. To post to this group, send email to [email protected]. 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/CACYTDBf0BNcKOJcM1%2BvqKpupg%3D9ybaoLeQ5iim%3DbYtwTXmMzYQ%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
