Re:Word generator using recurrent neural networks
by maxmcd on Sunday November 29, 2015 @07:00PM
(#10646761)
This seems to be the source: https://github.com/shariq/burgundy
Training word list: https://github.com/shariq/burgundy/blob/master/wordserver/ol...
Re:Word generator using recurrent neural networks
by cardigan on Monday November 30, 2015 @12:12AM
(#10647854)
Yes totally can be. Nothing English language specific about this. Scoring the models is a bit of a pain without a large corpus of English, but the training data was only 800 words.
Re:Word generator using recurrent neural networks
by igravious on Monday November 30, 2015 @05:02AM
(#10648642)
You said that you wrote a scoring function based on your subjective response to outputs. Supposedly if English is your native language (it seems to be) then you would have influenced the algorithm to home in on English phonology.
Surely?
I looked at about 20 words and they all seemed like decent English candidate words, including one actual English word, "molest".
Re:Word generator using recurrent neural networks
by cardigan on Monday November 30, 2015 @06:19AM
(#10648842)
The first kind of scoring function was language independent (e.g, penalize words showing up from the training set, penalize < 3 character words, penalize duplicate words, penalize common words), and the second scoring function needed a large training set of English words (but could be any other training set).
All this is described at the top. I guess you didn't read that.
It seems to only generate words that match English phonotactics & spelling conventions- things that could be English words. Can it be retargeted to other languages, or to arbitrary word-shape constraints?
I am particularly interested because I've recently undertaken a survey of word-generation software for conlangers (people who create artificial languages, like Quenya or Klingon or Na'vi), and while they do come in widely varying degrees of sophistication, with varying degrees of built-in linguistic knowledge, there are none yet publically available that are based on neural networks.