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": ...
Update Entity Type Version 2 for NLU pre annotation for supported languages
Although the latest version of NLU use Entity Type Version 2 for Italian and some other languages, WKS still uses NLU Version 1 for all languages, not just Italian.
Until WKS will use V1 version for pre annotation the new V2 entities will not be ...
Extract insights from an image using smart document understanding (WDS)
IBM Sellers, Offering managers and marketing team can extract
Use case1: Extract the company location in the magic quadrant like if IBM is listed in Leader's quadrant (Currently WDS can extract the list of companies present in the image)
Use case2...
Include Query parameter in results from the query and event log
When we query the /logs for a particular query ID, we can get the natural_language_query paratmer returned which contains the query string.
{ customer_id: '', environment_id: 'XXXX', natural_language_query: 'are there any capital metrics?', query_...
Stop words should not impact phrases in Discovery Query Language
WDS enables you to define your own set of stop words. We recently noticed that the stop words are removed from searches even when using phrases with the Discovery Language syntax. For example if we search for the phrase "we the people" and we and ...
LIBOR replacement in ISDA contracts between Banks and their clients
Most derivatives contracts currently written use ISDA contractual language and most of these also refer to LIBOR as the benchmark interest rates. By 2021 it has been mandated that LIBOR will be replaced, so there is a massive repapering exercise a...
Add standardization functionally to Task record(s) compare screen in Inspector
When viewing a tasks in Inspector, the compare screen of the attributes is not applying the standardization rules and therefor will indicate attributes are different when in fact to the algorithm, the are considered the same. We would like for ins...
It would be handy to be able to delete documents from a collection by defining conditions. Something I would do in a sql-database like this:
DELETE FROM collection_name WHERE publication_date < date('2018-01-01')