Re:How to Get into Natural Language Processing
by tyingq on Saturday January 21, 2017 @09:19AM
(#13450103)
I tried playing around with NLG a couple of years ago. The only tool I was able to get up and running well enough to do anything was SimpleNLG[1]. It's java, not my forte, but was straightforward otherwise. Here's a basic example of use: https://github.com/simplenlg/simplenlg/wiki/Section%20V%20%E...
Re:How to Get into Natural Language Processing
by mwexler on Friday January 20, 2017 @03:06PM
(#13446597)
+ this. It's actually much harder than folks think; most solutions are still rules and sentence fragments that you string append. Automated Insights and Narrative Science are both doing interesting work, but more is needed here.
(...though I don't agree that NLP is mature, just more mature than this. Lots of room to improve NLP as well!)
Re:How to Get into Natural Language Processing
by will_pseudonym on Friday January 20, 2017 @04:43PM
(#13447206)
I'm not sure what methods they use, but the "single sentence reply suggestions" created by Google's Inbox are the highest quality natural language generation that I have come across.
Re:How to Get into Natural Language Processing
by tyingq on Saturday January 21, 2017 @09:43AM
(#13450196)
I believe this is the paper that describes the approach they are using: http://www.kdd.org/kdd2016/papers/files/Paper_1069.pdf
Looks less like NLG, and more like picking existing responses from a (probably huge) corpus using ML. Hard to replicate unless you have access to the kind of data Google has.
Re:How to Get into Natural Language Processing
by will_pseudonym on Sunday January 22, 2017 @02:58AM
(#13454198)
If you think about it, all natural language generation is simply picking from a list of possible words to go next. They just do that at a sentence level.
Re:How to Get into Natural Language Processing
by tyingq on Sunday January 22, 2017 @10:55AM
(#13455664)
Heh. I suppose, if you have enough sentences to choose from for the various combinations of words, tenses, conjugations, prepositions, and so forth. Can't imagine there's many entities that would have that much data.
What I want are more tools for Natural Language Generation. Can anyone recommend some good ones? (beyond what's on Wikipedia)