fazel
/
spacy-fa-pipeline
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fa_ner_sm.cfg: fix stale header comment 

Described the shipped component as trained on ParsTwiNER (67.22 F); it has
trained on PerDT's own NER layer (71.87 F) since the treebank's NER layer was
found. Also updated the fa_core_news_sm reference from future tense to the
assemble-core step that already sources this component into it.
This commit is contained in:
Mohamad Fazeli 2026-08-02 20:38:45 +03:30
parent d5fadb07f0
commit 079663083a
Signed by: fazel
GPG Key ID: 05E227BF4D6736DE
1 changed files with 8 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
configs/fa_ner_sm.cfg
View File

@ -1,10 +1,11 @@
# fa_ent_news_sm — Persian NER, CPU size (sm).
#
# A standalone artifact, not part of the shipping `dep` pipeline. It is trained on
# ParsTwiNER (MIT, tweets) while the rest of the project trains on UD_Persian-PerDT
# (CC BY-SA 4.0, edited prose), and it scores 67.22 F against 85-98 for the UD
# components — different corpus, different genre, different quality tier, so it gets its
# own package rather than being hidden inside a `core` one. Built by `spacy project run ner`.
# Standalone package, built by `spacy project run ner`, sitting alongside (not inside)
# fa_dep_news_sm. Trained on the PerDT treebank's own NER layer (CC BY-SA 4.0, edited
# prose), transferred onto this project's tokenization by scripts/transfer_perdt_ner.py.
# Scores ENTS_F 71.87 on the PerDT test split; see docs/MODELS.md §3.2 for the corpus
# survey (ParsTwiNER, ARMAN, PEYMA and others were considered and rejected on licence or
# genre grounds).
#
# Deliberate deviation from `spacy init config --pipeline ner`: the tok2vec is
# EMBEDDED inside components.ner.model instead of being a separate `tok2vec`
@ -12,8 +13,8 @@
# it was trained in; embedding makes the component self-contained and therefore
# sourceable into another pipeline via `nlp.add_pipe("ner", source=...)`. This is the same
# design as en_core_web_sm, whose `ner` "has its own independent internal tok2vec"
# (https://spacy.io/models#design). That is what will let a future fa_core_news_sm combine
# this component (or its ../ner_dataset replacement) with the dep pipeline.
# (https://spacy.io/models#design). `assemble-core` in project.yml uses exactly that to
# source this component into fa_core_news_sm alongside the dep pipeline.
[paths]
train = null