Update curated.py

curated.py

@@ -464,7 +464,7 @@ filtering_process = Div(
         Ol(
             Li("Language Filter: any language other than English are discarded"),
             Li("Minimum Word Count Filter: less than 500 words (not inclusive) are discarded"),
-            Li("Unigram Log Probablity Filter: Documents were kept if they their average unigram log probability was higher than -20. To calculate the average log word probability, we use word frequencies extracted from the", A("1T Web-gram corpus", href= "https://catalog.ldc.upenn.edu/LDC2006T13"),". Specifically, we use the list available created by". A("Rachel Tatman", href="https://www.kaggle.com/datasets/rtatman/english-word-frequency"),"."),
+            Li("Unigram Log Probablity Filter: Documents were kept if they their average unigram log probability was higher than -20. To calculate the average log word probability, we use word frequencies extracted from the", A("1T Web-gram corpus", href= "https://catalog.ldc.upenn.edu/LDC2006T13"),". Specifically, we use the list available created by", A("Rachel Tatman", href="https://www.kaggle.com/datasets/rtatman/english-word-frequency"),"."),
             Li("Note: The Frequency Filter was calculated but not applied. The most frequent word in the paper consists of alpha characters only, and it appears in less than 7.5% of the document. Words are obtained by splitting the text on whitespace."),
         ),
         H4("Local Deduplication Process"),