Watson Discovery

Showing 246

Auto warning for unusual data trend

Auto warning or notification when system found unusual data compare to data history in certain period. It can be by color, text notification, etc. The purpose is just to notify user that there is unusual data or trend compare to certain period bac...

almost 5 years ago in Watson Discovery 0 Not under consideration

1 VOTE

Extract all properties from Word documents

WDS extract only few properties from a Word document, but some users more properties : example with Manager or Company or Category who are not extracted and indexed.All custom properties used as tags by users are also not extracted and not indexed...

almost 5 years ago in Watson Discovery 0 Not under consideration

1 VOTE

Display correct document names in the SDU interface.

Nokia is using WDS for their HR Chatbot, and trying out long tail search optimisation through SDU. Anyhow, in the SDU UI's dropdown file list, the files uploaded from the CAESAR/SEA (chatbot asset) Admin Panel to Discovery always get "_" as the ex...

almost 5 years ago in Watson Discovery 1 Functionality already exists

1 VOTE

Option to fetch Sub Types while exporting the WKS ML model to use in Content Analytics

We have a requirement to use WKS ML model in Content Analytics. I have created subtypes in the WKS model for better understanding of the data. But I am not able to fetch those subtypes while exporting as there is only option to use mentions and re...

about 5 years ago in Watson Discovery 0 Not under consideration

1 VOTE

question generation for uploaded content

The WDS primarily is focussed on answering a query based on documents ingested. In the education paradigm something additional important is being able to create questions (short-answer, fill-in-the-blanks, true or false or long answer) which that ...

over 5 years ago in Watson Discovery 1 Not under consideration

1 VOTE

More Feedback within the Crawler Sync Settings section of website

More feedback info on the crawler process is needed within the Sync Section of the WDS tooling site. It would be great to know the under of documents / web pages that had been ingested in each run of the crawler. Currently only the complete number...

over 5 years ago in Watson Discovery 0 Not under consideration

1 VOTE

Method / Option within Sync Setting to initiate a complete reload of the documents that have already been crawled.

Currently even if you make changes to the schedule or the SDU collection, which is the normal trigger to re-read a set of documents or Web site that has already been crawled. Documents that have not been altered / edited will not be include within...

over 5 years ago in Watson Discovery 0 Not under consideration

1 VOTE

Return Lemma for the sentences while using Rule Based model

Return Lemma for the sentences while using Rule Based model, Provide API access to retrun the lemma's ,surface forms

over 5 years ago in Watson Discovery 0 Not under consideration

1 VOTE

NLQ should not search numeric fields that specify e.g. offset of entity within text

The json document https://ibm.box.com/s/32mis3zwbzk3t913wdrbmcl30i3at129 ingested into WDS ends up with this out of the box NLU detected "Jobtitle" entity, with location offset ending at 2016: { "count": 2, "text": "program manager", "mentions": ...

over 5 years ago in Watson Discovery 1 Not under consideration

1 VOTE

Retain new line formatting with SDU

For customers who used non-SDU collections, some of them were using "html" field to retain formatting of text. Now with SDU, this feature is no longer there. We understand that retaining formatting is not possible in SDU. However, newlines are als...

over 5 years ago in Watson Discovery 1 Planned for future release

Please enter your email address

FILTER BY CATEGORY