Comment by binarymax
6 years ago
The results are just incredible. The depth of the project is very deep. Case in point, chess+clock yields hourglasker (hourglass & Lasker). Lasker was a German chess champion, well known in chess circles but the average person would have no idea who he is.
I wonder if this is using wikipedia or dbpedia to walk a graph and find words to stick together. That's the only way I could think of doing this.
That's really cool, but as I described above, my experience was different. The phoneme matching is really impressive but the word selection functionality seems pretty weak.
I had better luck with "large" and "cat" which gave me "colossalot", as in "colossal ocelot", which is a real winner.
However, I don't want to dismiss the hard work that went into this tool, despite my criticisms. It's very, very cool.
>Lasker was a German chess champion
That doesn't quite do him justice - Emanuel Lasker was world champion for 27 (!) years, 1894-1921, a record not likely ever to be surpassed. And a mathematician (e.g. see https://en.wikipedia.org/wiki/Laskerian_ring ) and fine writer. In fact I learnt to play from Lasker's Manual of Chess. It's very poetic in places, e.g.
On the chessboard, lies and hypocrisy do not survive long. The creative combination lays bare the presumption of a lie; the merciless fact, culminating in the checkmate, contradicts the hypocrite.
edit: I guess you knew that if you were trying chess + clock hehe.
Nope, the paper says it's just using the FastText word embedding: https://nips2018creativity.github.io/doc/entendrepreneur.pdf which is just a particularly well-done word2vec: https://arxiv.org/pdf/1712.09405.pdf 'Lasker' and 'chess' no doubt co-occur quite strongly in their Internet corpus.
On the other hand, it comes up with "Beagle" and "Labrador" as synonyms of "cat". Color me unimpressed.
This seems like something that has been done before, and the fact the paper has no references indicates to me that the author maybe didn't do background research. While [0] is different, I could have sworn I've seen a paper which discussed creating puns in this fashion.
[0] http://www.aclweb.org/anthology/W05-1614
Maybe you saw https://llamasandmystegosaurus.blogspot.com/2017/05/alpha.ht... a year or two ago which does something similar in generating rhyming definitions, also using a word2vec approach.
> On the other hand, it comes up with "Beagle" and "Labrador" as synonyms of "cat". Color me unimpressed.
'It doesn't matter whether a cat has floppy ears or yellow fur so long as it catches mice.'
1 reply →
fasttext and word2vec only encode contextual similarity, they're not meant to generate synonyms.
1 reply →