Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Rasa NLU: Open-source bot tool for natural language understanding

rasa.ai

Post reply on HN
Print view View original

11–20 of 23 posts

Re: Rasa NLU: Open-source bot tool for natural language understanding

#12

Post by ragebol »

Nice, I've been looking for an offline solution to do this sort of thing to run on a robot for RoboCup@Home.

Perhaps http://sag.art.uniroma2.it/demo-software/huric/ might also provide some training data. It's annoying though I can't just download that corpus but have to email some guy first.

Re: Rasa NLU: Open-source bot tool for natural language understanding

#16

Post by espadrine »

For NLP, they use either MITIE[0] or spaCy[1].

That said, from my experience, you can get surprisingly far with simple systems; for instance, queread[2] relies on graph learning and statistics.

[0]: https://github.com/mit-nlp/MITIE

[1]: https://spacy.io/

[2]: https://github.com/espadrine/queread#workings

Re: Rasa NLU: Open-source bot tool for natural language understanding

#17

Post by Rabidgremlin »

It's the "conversation" part that is really tricky... I have been working on a bot for a large Corp for the last few months and we have been using Inkle's Ink narration/dialog engine for this. Works very well. They let me open source the framework: https://github.com/rabidgremlin/Mutters it uses OpenNLP for intent identification and NER, Ink for conversation state and "scripting"

Re: Rasa NLU: Open-source bot tool for natural language understanding

#18

Post by Rabidgremlin »

bendyBus wrote: post #9
IshKebab wrote: post #5

A while ago I looked for information on how Alexa, Wit.ai, Nuance Mix etc. do this intent classification and didn't find anything. These guys have posted a nice blog post about their approach: https://conversations.golastmile.com/do-it-yourself-nlp-for-... They suggest that they add the word vectors in the sentence. But it seems to me that that would make the result independent of the order of words (i.e. "when does…

yeah you're quite right, intents are built with a bag of words model & doesn't take order into account. Entity extraction does though. If you find a case where word order is really important for getting intents right I'd love to know about it! We could find a way to make that work.

The bot I have been working on uses bag of words and n-grams to identify intents. Useful for when someone says something that may have multiple entities of the same type. For instance a journey start and end point. Can use the "from" and "to" words match better. Also very useful when training on phrases that are very similar such as FAQ questions which often have the same words but the order and one or two keys words is super important to get the right match.

Re: Rasa NLU: Open-source bot tool for natural language understanding

#19

Post by espadrine »

bendyBus wrote: post #9
IshKebab wrote: post #5

A while ago I looked for information on how Alexa, Wit.ai, Nuance Mix etc. do this intent classification and didn't find anything. These guys have posted a nice blog post about their approach: https://conversations.golastmile.com/do-it-yourself-nlp-for-... They suggest that they add the word vectors in the sentence. But it seems to me that that would make the result independent of the order of words (i.e. "when does…

yeah you're quite right, intents are built with a bag of words model & doesn't take order into account. Entity extraction does though. If you find a case where word order is really important for getting intents right I'd love to know about it! We could find a way to make that work.

> If you find a case where word order is really important for getting intents right

This may be facetious of me, since it's still fairly uncommon, but here it is.

Set up the go game, go up game the set.

State the ban law, ban the state law.

Drive the car by the park, park the car by the drive.

Post reply on HN