Spaces:
Runtime error
Runtime error
Update Space (evaluate main: e179b5b8)
Browse files
README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
---
|
| 2 |
title: SQuAD v2
|
| 3 |
-
emoji: 🤗
|
| 4 |
colorFrom: blue
|
| 5 |
colorTo: red
|
| 6 |
sdk: gradio
|
|
@@ -8,35 +8,10 @@ sdk_version: 3.0.2
|
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
tags:
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
description: >-
|
| 14 |
-
This metric wrap the official scoring script for version 2 of the Stanford
|
| 15 |
-
Question
|
| 16 |
-
|
| 17 |
-
Answering Dataset (SQuAD).
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
Stanford Question Answering Dataset (SQuAD) is a reading comprehension
|
| 21 |
-
dataset, consisting of questions posed by
|
| 22 |
-
|
| 23 |
-
crowdworkers on a set of Wikipedia articles, where the answer to every
|
| 24 |
-
question is a segment of text, or span,
|
| 25 |
-
|
| 26 |
-
from the corresponding reading passage, or the question might be unanswerable.
|
| 27 |
-
|
| 28 |
-
|
| 29 |
-
SQuAD2.0 combines the 100,000 questions in SQuAD1.1 with over 50,000
|
| 30 |
-
unanswerable questions
|
| 31 |
-
|
| 32 |
-
written adversarially by crowdworkers to look similar to answerable ones.
|
| 33 |
-
|
| 34 |
-
To do well on SQuAD2.0, systems must not only answer questions when possible,
|
| 35 |
-
but also
|
| 36 |
-
|
| 37 |
-
determine when no answer is supported by the paragraph and abstain from
|
| 38 |
-
answering.
|
| 39 |
---
|
|
|
|
| 40 |
# Metric Card for SQuAD v2
|
| 41 |
|
| 42 |
## Metric description
|
|
|
|
| 1 |
---
|
| 2 |
title: SQuAD v2
|
| 3 |
+
emoji: 🤗
|
| 4 |
colorFrom: blue
|
| 5 |
colorTo: red
|
| 6 |
sdk: gradio
|
|
|
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
tags:
|
| 11 |
+
- evaluate
|
| 12 |
+
- metric
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
---
|
| 14 |
+
|
| 15 |
# Metric Card for SQuAD v2
|
| 16 |
|
| 17 |
## Metric description
|