Re:Open Sourcing our new Duckling – Probabilistic Parser Rew...
by blandinw on Tuesday May 02, 2017 @09:40PM
(#14252369)
(disclaimer: I work on Duckling)
I don't know of any benchmarks. HeidelTime and SUTime are two solid projects... although the rule files [0][1] are a bit scary if you ask me :-).
Quick thoughts:
- SUTime relies on TokensRegex [2] which is similar to how Duckling parses sentences at a high-level
- SUTime seems to only provide English rules
- I don't know of any production use cases of either
[0] https://github.com/stanfordnlp/CoreNLP/tree/master/src/edu/s...
[1] https://github.com/HeidelTime/heideltime/blob/master/resourc...
Re:Open Sourcing our new Duckling – Probabilistic Parser Rew...
by nl on Wednesday May 03, 2017 @03:02AM
(#14253611)
Yes, the rules are horrible.
Yes, SUTime only has English rules
I don't know of any production use cases of either
Hi... Using SUTime for English, HeidelTime for non-English. Not at FB scale, but running against millions of messages per day.
Are there any benchmark for how well this compares with something like HeidelTime or SUTime[2]?
[1] https://github.com/HeidelTime
[2] https://nlp.stanford.edu/software/sutime.html