Gibberish Classifier with Elastic Search - Is it Possible?

Elastic Stack Elasticsearch
1

I have a system that stores user suggestions. Since the answers come from a
touchscreen, the kids love to insert comments like:

asduhaduh3189189'uih'dh
<3
asdasdasdas
gfdghgfhe
n035gh9091v

I created a bayesian classifier and trained it with thousands of answers.
Now it filters the user inputs quite well and very few gibberishes are
passing.
Although, I wanted to know if someone has faced similar problems and found
a way to deal with it using any Elastic Search capability.

How would you separate the gibberish from valid answers with ES?
Any idea?

Thanks

Mauricio Moraes

--
You received this message because you are subscribed to the Google Groups "elasticsearch" group.
To unsubscribe from this group and stop receiving emails from it, send an email to elasticsearch+unsubscribe@googlegroups.com.
To view this discussion on the web visit https://groups.google.com/d/msgid/elasticsearch/9c3c9421-9941-4859-9e82-2ef942742297%40googlegroups.com.
For more options, visit https://groups.google.com/d/optout.

2

Lucene comes with some classifier implementations, but they are not
integrated into Elasticsearch API yet.

For more details, see

http://soleami.com/blog/comparing-document-classification-functions-of-lucene-and-mahout.html

Jörg

On Mon, Oct 6, 2014 at 10:45 PM, Mauricio Moraes <
mauricioflaviomoraes@gmail.com> wrote:

I have a system that stores user suggestions. Since the answers come from
a touchscreen, the kids love to insert comments like:

asduhaduh3189189'uih'dh
<3
asdasdasdas
gfdghgfhe
n035gh9091v

I created a bayesian classifier and trained it with thousands of answers.
Now it filters the user inputs quite well and very few gibberishes are
passing.
Although, I wanted to know if someone has faced similar problems and found
a way to deal with it using any Elastic Search capability.

How would you separate the gibberish from valid answers with ES?
Any idea?

Thanks

Mauricio Moraes

--
You received this message because you are subscribed to the Google Groups
"elasticsearch" group.
To unsubscribe from this group and stop receiving emails from it, send an
email to elasticsearch+unsubscribe@googlegroups.com.
To view this discussion on the web visit
https://groups.google.com/d/msgid/elasticsearch/9c3c9421-9941-4859-9e82-2ef942742297%40googlegroups.com
https://groups.google.com/d/msgid/elasticsearch/9c3c9421-9941-4859-9e82-2ef942742297%40googlegroups.com?utm_medium=email&utm_source=footer
.
For more options, visit https://groups.google.com/d/optout.

--
You received this message because you are subscribed to the Google Groups "elasticsearch" group.
To unsubscribe from this group and stop receiving emails from it, send an email to elasticsearch+unsubscribe@googlegroups.com.
To view this discussion on the web visit https://groups.google.com/d/msgid/elasticsearch/CAKdsXoFtdOzOno48oFQnWZXpTX%3DcJJR-Dp16u2VSc6fr0RFj5w%40mail.gmail.com.
For more options, visit https://groups.google.com/d/optout.