Re:Ask HN: If you could talk to a database in plain English,...
by brochington on Friday June 24, 2022 @03:52PM
(#31868433)
1990's huh, wow. I totally believe it. It almost feels like a solved problem, but when I tried to find an API that parsed text to a degree that was usable by an average dev, nothing came up. Many NLP/AI/ML tools could define the entities, or VERY general relationships, but never went far enough. I'm curious if the 90's solutions used ML, or if they went straight to text analysis (which is what I'm using).
> Ultimately though, I think the usefulness of these tools breaks down for both complex queries and even simple ones when the data model does not have explicit relationships defined.
Makes sense. Do you think it would help if a developer could define the relationships in the data model ahead of time?
Re:Ask HN: If you could talk to a database in plain English,...
by getpost on Friday June 24, 2022 @04:15PM
(#31868716)
Symantec Q&A was released in 1985.
https://en.wikipedia.org/wiki/Q%26A_%28Symantec%29
For various definitions of query, the work goes back to the 1950s https://developer.ibm.com/articles/a-beginners-guide-to-natu...
Re:Ask HN: If you could talk to a database in plain English,...
by brochington on Friday June 24, 2022 @04:34PM
(#31868951)
The Symantec link is fascinating, thank you for that!
Ultimately though, I think the usefulness of these tools breaks down for both complex queries and even simple ones when the data model does not have explicit relationships defined.