explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-04-22 10:02:01 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix EL incl_context bug as in https://github.com/explosion/spaCy/pull/12398.

Browse Source
This commit is contained in:
Raphael Mitsch 2023-03-14 22:13:14 +01:00
parent 2fab08579f
commit 7851f6eb8e
1 changed files with 11 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
spacy/pipeline/entity_linker.py
View File

@ -499,13 +499,20 @@ class EntityLinker(TrainablePipe):
# Looping over candidate entities for this doc. (TODO: rewrite)
for ent_cand_idx, ent in enumerate(doc.ents):
sent_index = sentences.index(ent.sent)
assert sent_index >= 0
assert hasattr(ent, "sents")
sents = list(ent.sents)
sent_indices = (
sentences.index(sents[0]),
sentences.index(sents[-1]),
)
assert sent_indices[1] >= sent_indices[0] >= 0
if self.incl_context:
# get n_neighbour sentences, clipped to the length of the document
start_sentence = max(0, sent_index - self.n_sents)
end_sentence = min(len(sentences) - 1, sent_index + self.n_sents)
start_sentence = max(0, sent_indices[0] - self.n_sents)
end_sentence = min(
len(sentences) - 1, sent_indices[1] + self.n_sents
)
start_token = sentences[start_sentence].start
end_token = sentences[end_sentence].end
sent_doc = doc[start_token:end_token].as_doc()