Stack Overflow
Stack Overflow

Questions tagged [retrieve-and-rank]

Use the Retrieve and Rank tag when the question is about the IBM Watson Retrieve and rank service.

The IBM Watson Retrieve and Rank service helps users find the most relevant information for their query by using a combination of search and machine learning algorithms to detect "signals" in the data. Built on top of Apache Solr, developers load their data into the service, train a machine learning model based on known relevant results, then leverage this model to provide improved results to their end users based on their question or query.

Documentation: http://www.ibm.com/smarterplanet/us/en/ibmwatson/developercloud/doc/retrieve-rank/

94 questions
1
vote
0 answers

Retrieve and Rank sample (Watson service) and Android

I was trying to made a simple project with Retrieve and Rank service from IBM Watson. I have already a Collection, Cluster, and the Ranker is trained . Later I want to made a question to my service but I have problems with dependencies from…
Richard L.
  • 31
  • 4
1
vote
1 answer

How to resolve HTTP 403(requested via method [POST] has been blocked) error of R&R index documents API

I tried to index 2 million documents in R&R, but got a HTTP403 error after about 830 thousands documents. I sent 'update API' request with 10 thousands document at once and repeat the operation by my customized tool. I succeeded until about 830…
shimac-jp
  • 215
  • 3
  • 10
1
vote
1 answer

How to train the model using user clicks when use Solr ltr(learning to rank) module

In https://issues.apache.org/jira/browse/SOLR-8542, Solr integrates learning-to-rank function. I tried to integrate it into our product. But I am having difficult figuring out how to translate the partial pairwise feedback to the importance or…
jeffery.yuan
  • 975
  • 1
  • 13
  • 24
1
vote
1 answer

watson retrieve-and-rank - manual ranking

I am trying to build a ranker for a demonstration. I did the "automatic training" and i got OK results (could be better) I am trying to go into manual training but I am confuse about the meaning of the parameters from the Bluemix online…
Xavier Mary
  • 15
  • 4
1
vote
1 answer

Can I upload a zip file with htmls or a zip file with json files using the Web Interface of Watson Retrieve and Rank service?

Can I upload a zip file with htmls or a zip file with json files using the Web Interface of Watson Retrieve and Rank service ?
Salil Ahuja
  • 55
  • 3
1
vote
1 answer

Set Title and Id With Retrieve and Rank Web Interface

I have used IBM Watson Retrieve and Rank Web Interface to create a collection of html articles. Via the web interface I was able to upload my html articles. The problem is when I query the collection the data for id and title are not usable. Here…
John
  • 353
  • 1
  • 3
  • 11
1
vote
1 answer

Can Watson R&R service specify whether specific user can access to restricted answer?

As I know, Watson can provide relatively right answer with rank-confidence once user asks their question. But in real world, some restricted information must not be opened to every user. Can Watson learn about which answer must not be opened to…
Mathew
  • 11
  • 1
1
vote
1 answer

IBM Watson Retrieve and Rank Task are repeating after being completed

I have two collections in my Retrieve and Rank cluster. I have already completed TASKS for one collection and trained a ranker for it too. But, now when am training the second collection, my TASKS' QUESTIONS are repeating. This did not happen when I…
yadavankit
  • 325
  • 2
  • 12
1
vote
2 answers

Solr : curl command for adding new multi-term synonyms

We are trying to create/upload new synonyms to Solr as managed resources. We are facing some problems when we create multi-term synonyms like, for example, "United States of America" or "Spider Man". The Solr Documentation provides a curl command…
Daniel Moura
  • 21
  • 4
1
vote
2 answers

Solr : curl command to create multi term synonyms

We are trying to perform this curl command: curl -X POST -H "Content-type:application/json" -u "USERNAME":"PASSWORD"…
Daniel Moura
  • 21
  • 4
1
vote
0 answers

Unable to upload solr config to Watson's retrieve and rank using their Java API

I'm trying out IBM Watson's Retrieve and Rank service and I want to try to replicate the demo (Cranfield data) using Java. I am not familiar with Apache Solr, so I just used the [cranfield-solr-config.zip] file used in the…
sikidhart
  • 351
  • 2
  • 11
1
vote
1 answer

How to format .DOC documents for Watson retrieve and rank web interface uploader

I wonder what is the best way to format .DOC documents for Retrieve and Rank web interface document uploader so it handles the answer splitting the best. (I am using https://watson-retrieve-and-rank.ng.bluemix.net ) We have to create a set of…
icordoba
  • 1,570
  • 21
  • 54
1
vote
0 answers

indexing stops after solr.Solr Mapping Reader

I am trying to index my Nuch crawled data by the following command : bin/nutch index -D solr.server.url="https://gateway.watsonplatform.net/retrieve-and-rank/api/v1/solr_clusters/sc97b4177a_600f_4040_9309_e632c116443f/solr/localWebCollection/" -D…
S.Doe
  • 39
  • 9
1
vote
2 answers

Indexing nutch crawled data in "Bluemix" solr

I'm trying to index the nutch crawled data by Bluemix solr and I cannot find anyway to do it. My main question is: Is there anybody that can help me to do so? what should I do to send the result of my nutch crawled data to my Blumix Solr. For the…
S.Doe
  • 39
  • 9
1
vote
1 answer

Custom UIMA annotators in IBM Watson Retrieve&Rank

Is it possible to use custom uima annotators in Retrieve&Rank service? How can I upload my custom annotator (packaged as jar file) to the service? I need to create an entity annotator to discover my custom domain entities.
Premier
  • 3,952
  • 6
  • 39
  • 56
1
2
3 4 5 6 7