victormiller commited on
Commit
adfc108
1 Parent(s): 82be905

Update curated.py

Browse files
Files changed (1) hide show
  1. curated.py +1 -1
curated.py CHANGED
@@ -688,7 +688,7 @@ filtering_process = Div(
688
  Li(P(B("CID Percentage Filter: "), "removes LaTex heavy paragraphs that contain over 10% “CID” font artifacts.")),
689
  Li(P(B("Letterness Filter: "), "discards paragraphs with a low proportion of letters")),
690
  Li(P(B("Removing Leading/Trailing Numbers: "), "removes numbers at the start or end of paragraphs. ", D_code("1 This is a sentence.", language="python"), " becomes ", D_code("This is a sentence.", language="python")))),
691
- Li(P(B("Fixing Unicode Issues: "), "fixes Unicode issues.",)),
692
  Li(P(B("Combining Diacritics Correction: "), D_code("a'", language="python"), " becomes ", D_code("å", language="python")))),
693
  Li(P(B("Unigram Log Probability: "), "the document must have higher than -20 average unigram log probability.")),
694
  ),
 
688
  Li(P(B("CID Percentage Filter: "), "removes LaTex heavy paragraphs that contain over 10% “CID” font artifacts.")),
689
  Li(P(B("Letterness Filter: "), "discards paragraphs with a low proportion of letters")),
690
  Li(P(B("Removing Leading/Trailing Numbers: "), "removes numbers at the start or end of paragraphs. ", D_code("1 This is a sentence.", language="python"), " becomes ", D_code("This is a sentence.", language="python")))),
691
+ Li(P(B("Fixing Unicode Issues: "), "fixes Unicode issues.")),
692
  Li(P(B("Combining Diacritics Correction: "), D_code("a'", language="python"), " becomes ", D_code("å", language="python")))),
693
  Li(P(B("Unigram Log Probability: "), "the document must have higher than -20 average unigram log probability.")),
694
  ),