feat: clean up exclude_headers

OpenBioML · Oct 11, 2023 · 8f0ebe1 · 8f0ebe1
1 parent a1af563
commit 8f0ebe1
Showing 1 changed file with 3 additions and 14 deletions.
diff --git a/data/natural/preprocess_nougat.py b/data/natural/preprocess_nougat.py
@@ -119,24 +119,17 @@ def remove_header(mmd, header_span):
 exclude_headers = [
     "accession codes",
     "acknowledgement",
-    "acknowledgements",
     "acknowledgment",
-    "acknowledgments",
     "additional files",
     "additional information",
     "associated content",
     "author contributions",
-    "author information",
-    "author",
-    "authors",
+    "author",  # incl: "author information", "corresponding author",
     "bibliography",
     "code availability",
     "competing interest",
-    "competing interests statement",
-    "competing interests",
     "conflict of interest",
     "conflicts of interest",
-    "corresponding author",
     "data and software availability",
     "data availability",
     "declaration of competing interest",
@@ -145,23 +138,19 @@ def remove_header(mmd, header_span):
     "financial support",
     "funding acs",
     "funding sources",
-    "graphical toc entry",
+    "graphical toc",
     "graphical abstract",
     "keywords",
     "note",
-    "notes",
     "orcid",
     "present address",
     "reference",
-    "references",
     "supplementary material",
     "supporting formation available",
-    "supporting information available",
     "supporting information",
     "table of contents",
-    # "toc",  # creates false positives
-    "corresponding authors:",
     # "abbreviations",
+    # "toc",  # creates false positives
 ]