My votes: Natural Language Understanding (NLU)

Showing 21

Ability to return sub section of identified regex as entity

We can identify any regular expression but can we *return specific part of extraction as entity* .e.g. regex is TN(\s)?(#)?(\s)?[0-9]{6,10} , I wish to identify whole expression and return only last identified number. TN # 12345689 From about ex...

almost 5 years ago in Natural Language Understanding (NLU) 0 Not under consideration

1 VOTE

Faster response from NLU RBR every time.

RBR models tend to give Downstream error or loads late for the first time after delay like 15 min. Custer feels RBR is unstable and inconsistent which is reducing the use of RBR model. Where as ML model does not show any such issues, Ideally we...

almost 5 years ago in Natural Language Understanding (NLU) 0 Not under consideration

1 VOTE

Polish language support

Please, add Polish language support for your NLU services.

over 5 years ago in Natural Language Understanding (NLU) 0 Not under consideration

1 VOTE

Natural Language Classifier -- For adding the Tamil Language

NLP Exist only for below mentioned Languages .Could you please add Tamil Language also. For any R&D ,I am ready to support.Tamil is very traditional old Language 100+ million people speaking and using this Language around the globe. (Natur...

over 5 years ago in Natural Language Understanding (NLU) 0 Not under consideration

1 VOTE

Recognize date/time (similar to Watson Assistant System entity)

for many tasks that are time/date based it would be really useful to be able to recognize common terms that represent actual time/dates and be able to get the specific date/time referenced (including relative date/time). For example: "Let's meet ...

almost 6 years ago in Natural Language Understanding (NLU) 0 Not under consideration

1 VOTE

Create a rest endpoint to duplicate WKS custom model instance.

Currently, we are unable to scale to more than 20 threads when using a WKS custom model for entity and relation prediction with the NLU service. Our documents are very large and one document can take up to 5 minutes to process. If we have multiple...

over 6 years ago in Natural Language Understanding (NLU) 0 Not under consideration

1 VOTE

Remove session cookie from NLU calls

When I use postman I am returned a cookie that allows me to make unauthenticated calls into the NLU system. This leads to a vulnerable API due to session hijacking. [1] To test this I made a call to get a list of models, removed my auth head, and ...

over 6 years ago in Natural Language Understanding (NLU) 1 Not under consideration

0 VOTE

Support for Chinese (Traditional and Simplified) Language

No description provided

over 5 years ago in Natural Language Understanding (NLU) 2 Not under consideration

0 VOTE

Restore types for concepts

Alchemy had types associated with concepts, but Discovery does not. It was useful to filter returned concepts to remove people and locations, particularly if we were displaying those elsewhere. The people returned as concepts, for example, were of...

almost 6 years ago in Natural Language Understanding (NLU) 0 Not under consideration

0 VOTE

Relation argument offsets relative to the html

The relation argument offsets come back relative to the Discovery text, but if you want to do something useful with those offsets it would probably be to add tags to the html. Computing the corresponding offset in the html is possible, but inconve...

almost 6 years ago in Natural Language Understanding (NLU) 0 Not under consideration

Please enter your email address

FILTER BY CATEGORY