renard-pipeline 0.4.1__py3-none-any.whl → 0.4.2__py3-none-any.whl

renard/pipeline/character_unification.py

@@ -159,6 +159,7 @@ class GraphRulesCharacterUnifier(PipelineStep):
         min_appearances: int = 0,
         additional_hypocorisms: Optional[List[Tuple[str, List[str]]]] = None,
         link_corefs_mentions: bool = False,
+        ignore_lone_titles: Optional[Set[str]] = None,
     ) -> None:
         """
         :param min_appearances: minimum number of appearances of a
@@ -173,10 +174,14 @@ class GraphRulesCharacterUnifier(PipelineStep):
             extract a lot of spurious links.  However, linking by
             coref is sometimes the only way to resolve a character
             alias.
+        :param ignore_lone_titles: a set of titles to ignore when
+            they stand on their own.  This avoids extracting false
+            positives characters such as 'Mr.' or 'Miss'.
         """
         self.min_appearances = min_appearances
         self.additional_hypocorisms = additional_hypocorisms
         self.link_corefs_mentions = link_corefs_mentions
+        self.ignore_lone_titles = ignore_lone_titles or set()
 
         super().__init__()
 
@@ -197,11 +202,16 @@ class GraphRulesCharacterUnifier(PipelineStep):
         import networkx as nx
 
         mentions = [m for m in entities if m.tag == "PER"]
-        mentions_str = [" ".join(m.tokens) for m in mentions]
+        mentions_str = set(
+            filter(
+                lambda m: not m in self.ignore_lone_titles,
+                map(lambda m: " ".join(m.tokens), mentions),
+            )
+        )
 
         # * create a graph where each node is a mention detected by NER
         G = nx.Graph()
-        for mention_str in set(mentions_str):
+        for mention_str in mentions_str:
             G.add_node(mention_str)
 
         # * HumanName local configuration - dependant on language

{renard_pipeline-0.4.1.dist-info → renard_pipeline-0.4.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: renard-pipeline
-Version: 0.4.1
+Version: 0.4.2
 Summary: Relationships Extraction from NARrative Documents
 Home-page: https://github.com/CompNet/Renard
 License: GPL-3.0-only

{renard_pipeline-0.4.1.dist-info → renard_pipeline-0.4.2.dist-info}/RECORD

@@ -3,7 +3,7 @@ renard/graph_utils.py,sha256=5jwky9JgJ-WMVHfeaiXkAAQwEfhR2BFSrWhck1Qmpgo,5812
 renard/ner_utils.py,sha256=jN1AQkaV0Kx-Bc0oc3SYBEmSUuKPBbzXqByOlaqH62k,11263
 renard/nltk_utils.py,sha256=mUJiwMrEDZV4Fla7WuMR-hA_OC2ZIwSXgW_0Ew18VSo,977
 renard/pipeline/__init__.py,sha256=8Yim2mmny8YGvM7N5-na5zK-C9UDxUb77K9ml-VirUA,35
-renard/pipeline/character_unification.py,sha256=GcnC8UYqn1RBOGVhYS9LVcTNqpxm9YoT-lPsE3vodek,14818
+renard/pipeline/character_unification.py,sha256=GJvPKw2zSMi0RpLLVlKsu7ewpxkrdxytND9PLxolbP4,15252
 renard/pipeline/characters_extraction.py,sha256=NzF8H9X19diW6rqwS5ERrRku7rFueO3S077H5C6kb7I,363
 renard/pipeline/core.py,sha256=luKNUTCDtZfwKzxVIaImyIMwFFvIknfT1LdQtongj24,22570
 renard/pipeline/corefs/__init__.py,sha256=9c9AaXBcRrDBf1jhTtJ7DyjOJhX_Zej3FjlcGak7MK8,44
@@ -29,7 +29,7 @@ renard/resources/pronouns/pronouns.py,sha256=YJ8hM6H8QHrF2Xx6O5blqc-Sqe1D1YFL0sR
 renard/resources/titles/__init__.py,sha256=Jcg4B7stsWiAaXbFgNl_L3ICtCQmFe9bo3YjdkVL50w,45
 renard/resources/titles/titles.py,sha256=GsFccVJuTkgDWiAqWZpFd2R9pGvFKQZBOk4RWWuWDkw,968
 renard/utils.py,sha256=8J3swFqSi4YqhgYNXvttJ0s-DmJbl_yEYri6JpGEWH8,2340
-renard_pipeline-0.4.1.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-renard_pipeline-0.4.1.dist-info/METADATA,sha256=KgpnPAR6BtLS4RNjsxIBWqUygUcoRdJfkqHigzZMSqU,3697
-renard_pipeline-0.4.1.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
-renard_pipeline-0.4.1.dist-info/RECORD,,
+renard_pipeline-0.4.2.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+renard_pipeline-0.4.2.dist-info/METADATA,sha256=R1ZbG6Mdk1B5Zk73QSKB-lZu7rDnvWKe3M5JiDqPFxM,3697
+renard_pipeline-0.4.2.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+renard_pipeline-0.4.2.dist-info/RECORD,,

{renard_pipeline-0.4.1.dist-info → renard_pipeline-0.4.2.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 1.5.2
+Generator: poetry-core 1.9.0
 Root-Is-Purelib: true
 Tag: py3-none-any