Extract only simple NPs from Penn Treebank

kornai · Jul 27, 2018 · c498a88 · c498a88
1 parent 15e9b83
commit c498a88
Showing 1 changed file with 3 additions and 2 deletions.
diff --git a/exp/alto/tools/get_nps_from_treebanks.py b/exp/alto/tools/get_nps_from_treebanks.py
@@ -4,5 +4,6 @@
     tree_file = "wsj_{}.mrg".format(str(n).zfill(4))
     sentences = treebank.parsed_sents(tree_file)
     for s in sentences:
-        for subtree in s.subtrees(lambda t: t.label().startswith("NP")):
-            print(subtree)
+        for subtree in s.subtrees(lambda t: t.label() == "NP"):
+            print(subtree.pformat(100000))
+            #print(subtree)