Spaces:
Runtime error
Runtime error
Style
Browse files
app.py
CHANGED
|
@@ -29,16 +29,20 @@ LOCAL_REPO = "submission_repo"
|
|
| 29 |
st.title("GEM Submissions")
|
| 30 |
st.markdown(
|
| 31 |
"""
|
| 32 |
-
Welcome to the [GEM benchmark](https://gem-benchmark.com/)! GEM is a benchmark
|
|
|
|
|
|
|
| 33 |
|
| 34 |
-
GEM aims to:
|
| 35 |
|
| 36 |
-
- measure NLG progress across many NLG tasks across languages.
|
| 37 |
-
- audit data and models and present results via data cards and model robustness
|
| 38 |
-
|
|
|
|
|
|
|
| 39 |
|
| 40 |
-
Use this page to submit your system's predictions to the benchmark.
|
| 41 |
-
"""
|
| 42 |
)
|
| 43 |
|
| 44 |
with st.form(key="form"):
|
|
|
|
| 29 |
st.title("GEM Submissions")
|
| 30 |
st.markdown(
|
| 31 |
"""
|
| 32 |
+
Welcome to the [GEM benchmark](https://gem-benchmark.com/)! GEM is a benchmark
|
| 33 |
+
environment for Natural Language Generation with a focus on its Evaluation, both
|
| 34 |
+
through human annotations and automated Metrics.
|
| 35 |
|
| 36 |
+
GEM aims to:
|
| 37 |
|
| 38 |
+
- measure NLG progress across many NLG tasks across languages.
|
| 39 |
+
- audit data and models and present results via data cards and model robustness
|
| 40 |
+
reports.
|
| 41 |
+
- develop standards for evaluation of generated text using both automated and
|
| 42 |
+
human metrics.
|
| 43 |
|
| 44 |
+
Use this page to submit your system's predictions to the benchmark.
|
| 45 |
+
"""
|
| 46 |
)
|
| 47 |
|
| 48 |
with st.form(key="form"):
|