Handle standalone past verbs tagged as participles

2026-11-04 16:40:13 +08:00
parent eb5c156104
commit 688613878f
1 changed files with 5 additions and 1 deletions
@@ -80,6 +80,10 @@ class Encoder:
        clauses = []
        proposals = []
        for sentence in doc.sents:
+            content = [token.i for token in sentence if not token.is_space]
+            if not content:
+                continue
+            sentence = doc[content[0]:content[-1] + 1]
            match = self._causal_marker(sentence)
            if match is None:
                continue
@@ -112,7 +116,7 @@ class Encoder:
            or not marker.i < verb.i < end
            or sentence.root.pos_ != "VERB"
            or verb.pos_ != "VERB"
-            or sentence.root.tag_ != "VBD"
+            or sentence.root.tag_ not in {"VBD", "VBN"}
            or verb.tag_ != "VBD"
            or any(token.is_punct or token.is_space for token in sentence[:-1])
            or any(token.dep_ in {"neg", "aux", "conj"} for token in sentence)