From 9d33a03f0425a0b0fbe9f312cc30e13c762234d0 Mon Sep 17 00:00:00 2001 From: Ankur Goyal Date: Tue, 6 Sep 2022 11:03:39 -0700 Subject: [PATCH] Improve titles --- README.md | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/README.md b/README.md index 034bc0a..ae879aa 100644 --- a/README.md +++ b/README.md @@ -18,8 +18,13 @@ invoices as well as both [SQuAD2.0](https://huggingface.co/datasets/squad_v2) an 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 classifier head. For example, QA models often encounter this failure mode: +### Before + ![Broken Address](./before.png) + +### After + However this model is able to predict non-consecutive tokens and therefore the address correctly: ![Two-line Address](./after.png)