Spaces:
Running
Running
typos
Browse files- harim_plus.py +4 -1
harim_plus.py
CHANGED
|
@@ -42,7 +42,7 @@ _CITATION = """\
|
|
| 42 |
}
|
| 43 |
"""
|
| 44 |
|
| 45 |
-
_DESCRIPTION = f"""HaRiM+ is a reference-less evaluation metric (i.e. requires only article-summary pair, no reference summary) for summarization which
|
| 46 |
Summarization model inside the HaRiM+ will read and evaluate how good the quality of a summary given the paired article.
|
| 47 |
It will work great for ranking the summary-article pairs according to its quality.
|
| 48 |
|
|
@@ -51,6 +51,9 @@ HaRiM+ is proved effective for benchmarking summarization systems (system-level
|
|
| 51 |
NOTE that for HaRiM+...
|
| 52 |
* predictions = summaries (List[str])
|
| 53 |
* references = articles (List[str])
|
|
|
|
|
|
|
|
|
|
| 54 |
"""
|
| 55 |
|
| 56 |
_KWARGS_DESCRIPTION = """
|
|
|
|
| 42 |
}
|
| 43 |
"""
|
| 44 |
|
| 45 |
+
_DESCRIPTION = f"""HaRiM+ is a reference-less evaluation metric (i.e. requires only article-summary pair, no reference summary) for summarization which leverages the power of summarization model.
|
| 46 |
Summarization model inside the HaRiM+ will read and evaluate how good the quality of a summary given the paired article.
|
| 47 |
It will work great for ranking the summary-article pairs according to its quality.
|
| 48 |
|
|
|
|
| 51 |
NOTE that for HaRiM+...
|
| 52 |
* predictions = summaries (List[str])
|
| 53 |
* references = articles (List[str])
|
| 54 |
+
|
| 55 |
+
Also Note that
|
| 56 |
+
* higher score = better quality
|
| 57 |
"""
|
| 58 |
|
| 59 |
_KWARGS_DESCRIPTION = """
|