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/

95 questions
1
vote
2 answers

Re-training Approach for NLC or R&R

The ground truth we know is used to re-train the NLC or R&R. The ground truth is a question level training data. e.g. "How hot is it today?,temperature" The question "how hot is it today?" is therefore classified to "temperature" class. Once the…
kwshiu
  • 11
  • 2
1
vote
1 answer

Updating schema for a IBM Watson Retrieve and Rank Config

Are there ways to update the schema of the Solr config in IBM Watson's Retrieve and Rank service other than deleting, then uploading the config again. I used the following example to create a new cluster, config and…
nodej
  • 11
  • 1
0
votes
1 answer

Having an error when installing Scann on Google Colab

I installed scann on colab with code !pip uninstall protobuf>=3.20.3 but I had a error like that: "ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the…
vinh nguyen
  • 1
0
votes
1 answer

Proper Formatting of Data for Watson Retrieve & Rank

Thanks for your time. I would like to know your thoughts on the best practice for formatting specific data to be uploaded to Watson Retrieve and Rank. I am building a service for answering questions about municipal laws and ordinances to help…
Matt Trahan
  • 13
  • 1
0
votes
1 answer

Watson Retrieve and Rank/ Discovery Service return always table of content with high(est) score

Backgroud: I'm using Watson Retrieve and Rank/ or Discovery Service to retrieve information from user manuals. I performed the training with an example washing machine manual in pdf format. My target is to receive the best passages from the…
Bene
  • 209
  • 1
  • 9
0
votes
1 answer

Retrieve and Rank IBM

In IBM Rank and Retrieve, is it possible to use your own Solr Cluster to save on expenses? If so, how? I am creating a chatbot and require Retrieve and Rank for the same. The IBM free service seems to have only a 50MB limit to the solr cluster. Is…
Anon
  • 3
  • 1
0
votes
1 answer

IBM watson rank and retrieve training the ranker getting Value error: No JSON could be decoded

I am trying to use the IBM Watson Rank and Retrieve service and I am following the tutorial with the sample data present in the portal i.e cranfield-data. However when I am trying to train the ranker using train.py I am getting the following…
majumderS
  • 21
  • 5
0
votes
2 answers

Watson Retrieve and Rank Questions Upload Failed

I've been working on a project involving the Watson Retrieve and Rank service and it was acting normally until now. I managed to upload a number of documents and created roughly 50 questions to start off. Normally, I was able to upload the questions…
Daniel Kovalevich
  • 1
  • 1
0
votes
1 answer

How to train multiple forms of the same query in R-n-R, instead uploading variation of the query & training it?

As I understand that in retrieve and rank we need to upload documents followed with questions for training purpose. - So, like in Watson Conversation we have entities and synonyms that can be added as a dictionary. Do we have a similar feature in…
Saurav Raiguru
  • 1
0
votes
1 answer

Conversation & Retrieve and Rank

After calling retrieve and rank in conversation using context variable, for example, I go to the JSON of the conversation and create a variable: ("call_retrieve_and_rank": true) On my server (python) When this variable is true, it searches the…
Gabriel Custódio Eng
  • 71
  • 4
0
votes
1 answer

IBM Bluemix error"You are using pip version 8.1.1, however version 9.0.1 is available"

I have tried to deploy my app on IBM Bluemix from the GitHub source.The app is started, but I got the following error: 2017-04-27T23:14:35.89-0700 [STG/0] ERR DEPRECATION: --allow-all-external has been deprecated and will be removed in the…
Mani kannan
  • 9
  • 4
0
votes
1 answer

IBM Watson retrieve and rank service - boolean operator

I'm writing the csv file to train a ranker in Watson Retrieve and Rank service, with many rows [query,"id_doc","relevance_score",...]. I have two questions about the structure of this file: I have to distinguish two documents, depending on whether…
Robychan
  • 45
  • 1
  • 6
0
votes
1 answer

Watson Retrieve and Rank service returns no search results, and a Solr error when trying to train Ranker with custom features

so I have the following problem: When I try to use the Ranker I have trained to search I get the following error message: pysolr.SolrError: Solr responded with an error (HTTP 500): [Reason: Can not rerank results. Verify that your schema has not…
Nikita
  • 23
  • 6
0
votes
1 answer

Only the number of questions of ground truth affects the size of R&R training data?

I created training data of R&R from ground truth and noticed that each question of ground truth made 10 records of training data without depending on the number of candidate answers of ground truth. Only the number of questions of ground truth…
shimac-jp
  • 233
  • 3
  • 11
0
votes
1 answer

IBM Watson Retrieve and Rank: Ranker training failure

I'm following this Tutorial. I've successfully completed Stage 3. Now in stage 4, I downloaded the sample ground truth and tried to create the ranker using REST API. The ranker is created with status as training. When I try to get that ranker by its…
Pratik Patil
  • 99
  • 1
  • 7
1 2
3
4 5 6 7