Ankur Goyal
commited on
Commit
·
0771b61
1
Parent(s):
1a67f8e
Improve README
Browse files
README.md
CHANGED
@@ -16,9 +16,13 @@ invoices as well as both [SQuAD2.0](https://huggingface.co/datasets/squad_v2) an
|
|
16 |
## Non-consecutive tokens
|
17 |
|
18 |
Unlike other QA models, which can only extract consecutive tokens (because they predict the start and end of a sequence), this model can predict longer-range, non-consecutive sequences with an additional
|
19 |
-
classifier head. For example,
|
20 |
|
21 |
-

|
22 |
+
|
23 |
+
However this model is able to predict non-consecutive tokens and therefore the address correctly:
|
24 |
+
|
25 |
+

|
26 |
|
27 |
## Getting started with the model
|
28 |
|
after.png
ADDED
![]() |
before.png
ADDED
![]() |
demo.png
DELETED
Binary file (630 kB)
|
|