Watson Discovery

Showing 246

Skipping processing of image files (JPG/GIF/PNG/image PDF)

Watson Discovery ingests a number of file types, including image types like JPG/GIF/PNG/image PDF. When OCR is switched off, Discovery still processes these files and captures its metadata. Our client wants to skip image files completely and also ...

about 2 years ago in Watson Discovery 0 Not under consideration

4 VOTE

Discovery highlight feature should exclude text inside image / anchor tags in html

Discovery highlight feature should exclude text inside image / anchor tags in html Currently it searches entire html for highlight feature an inserts <em> </em> tags inside img tags or anchor tags also which then cause issues when the ...

about 4 years ago in Watson Discovery 0 Not under consideration

4 VOTE

Handle rating scale conversions between Documents rated using API and documents rated using Static relevancy training

Handle rating scale conversions between Documents rated using API and documents rated using Static relevancy training. We are an OEM partner of IBM and have built a Chatbot integration with Watson Discovery search. The end Users of Chatbot rate in...

about 4 years ago in Watson Discovery 0 Not under consideration

6 VOTE

Ability to do semantic search

Currently first level search in WDS is based on term overlap which can be improved with relevancy training. The term overlap can be improved with query expansion. Now for a query on "car", customer also wants to retrieve documents on "Vehicle", "M...

over 6 years ago in Watson Discovery 3 Not under consideration

6 VOTE

Standard WDS crawler for websites

The standard WDS crawler supports filesystem, sharepoint and databases. Since one of the few document types that WDS can ingest is HTML, it would make sense to have the standard crawler also support HTTP and HTTPS accessible websites. https://bigb...

over 6 years ago in Watson Discovery 1 Functionality already exists

6 VOTE

Service for Users to Create Japanese Morpheme Dictionary/Japanese Stop-words Dictionary for Every Account at Any Time.

Japanese morphological analysis seems very difficult because we write the document in Japanese without spaces(e.g. 私の友達は食べることが大好きです。).That’s why my idea is to create Japanese morpheme dictionary/Japanese stop-words dictionary for every account at ...

almost 7 years ago in Watson Discovery 0 Not under consideration

3 VOTE

About available languages of when defining Entity/Relation in Knowledge Studio.

I would like to request Japanese added to characters that can be used for Entities/Relations in Knowledge Studio. (This request is strongly seek by our clients of a major cosmetics manufacturer that has expanded worldwide through our Project.) the...

over 3 years ago in Watson Discovery 0 Future consideration

1 VOTE

WD - Support custom tokenization dictionaries

In a project of moving from WKS to WD Entity Extractor, our customer needs the support for Dictionary-based tokenization. In current use case, there are some recurring scenarios that contains dotted words, like "sentenza n. 151", D.P.R. 45/2002" A...

about 1 year ago in Watson Discovery 0 Not under consideration

6 VOTE

Extend document removal API to work with removal queries

There have been several issues discovered when working with discovery and very dynamic date / agile prototyping. It is not possible (currently) to remove multiple documents, just 1 at a time. Often in the beginning of a project the data is ingeste...

almost 7 years ago in Watson Discovery 0 Not under consideration

4 VOTE

Multiple rankers per collection

Are there any plans to suppport more than one ranker for a given Discovery collection. This would help us train and test a "ranker B" while "ranker A" is in production. The alternative that we see is to create duplicate/synched Discovery collectio...

over 4 years ago in Watson Discovery 0 Not under consideration

Please enter your email address

FILTER BY CATEGORY