This writeup explains (with a sample) how ECTOR learns a sentence by integrating it into its Concept Network. Let's see on an example in what order to integrate words in the Concept Network. Here is a part of the initial Concept Network:
+-------(1)-----> program (1)
|
ECTOR (5) <----(2)----> is (3) <----(3)----> a (3) <----(1)----> bot (2)
|
Achille (1) <----(1)----+
Now, let's consider the sentence to integrate: Achille is a program.
- Adding of occurrences and co-occurrences:
Achille (2) <----(2)----> is (4) <----(4)----> a (4) <----(2)----> program (2)
- Expression/concept detection (co-occ >= MinCo-occ = 4):
+--------------> Achille is a program (1) <--------------+
| ^ |
| | |
| (1) |
(1) | (1)
| v |
| +-(4)--> is a (4) <--(4)-+ |
| | | |
v v v v
Achille (2) <--(2)--> is (4) <-----(4)-----> a (4) <--(2)--> program (2)
- Labels detection (simplified figure):
+-----> Achille is a program (1) <----+
| ^ |
| | |
(1) (1) (1)
| | | ======> is a (4)
v v v |
Achille(2) <--(2)--> is a (4) <--(2)--> program (2) Achille (2) <--(1)--> Program (2)