spaCy/bin/wiki_entity_linking
Sofie Van Landeghem 7b96a5e10f Reduce mem usage in training Entity Linker (#4811)
* move nlp processing for el pipe to batch training instead of preprocessing

* adding dev eval back in, and limit in articles instead of entities

* use pipe whenever possible

* few more small doc changes

* access dev data through generator

* tqdm description

* small fixes

* update documentation
2020-01-06 14:59:50 +01:00
..
README.md Reduce mem usage in training Entity Linker (#4811) 2020-01-06 14:59:50 +01:00
__init__.py KB extensions and better parsing of WikiData (#4375) 2019-10-14 12:28:53 +02:00
entity_linker_evaluation.py Reduce mem usage in training Entity Linker (#4811) 2020-01-06 14:59:50 +01:00
kb_creator.py KB extensions and better parsing of WikiData (#4375) 2019-10-14 12:28:53 +02:00
train_descriptions.py KB extensions and better parsing of WikiData (#4375) 2019-10-14 12:28:53 +02:00
wiki_io.py KB extensions and better parsing of WikiData (#4375) 2019-10-14 12:28:53 +02:00
wiki_namespaces.py KB extensions and better parsing of WikiData (#4375) 2019-10-14 12:28:53 +02:00
wikidata_pretrain_kb.py KB extensions and better parsing of WikiData (#4375) 2019-10-14 12:28:53 +02:00
wikidata_processor.py KB extensions and better parsing of WikiData (#4375) 2019-10-14 12:28:53 +02:00
wikidata_train_entity_linker.py Reduce mem usage in training Entity Linker (#4811) 2020-01-06 14:59:50 +01:00
wikipedia_processor.py Reduce mem usage in training Entity Linker (#4811) 2020-01-06 14:59:50 +01:00

README.md

Entity Linking with Wikipedia and Wikidata

Step 1: Create a Knowledge Base (KB) and training data

Run wikipedia_pretrain_kb.py

  • This takes as input the locations of a Wikipedia and a Wikidata dump, and produces a KB directory + training file
  • You can set the filtering parameters for KB construction:
    • max_per_alias (-a): (max) number of candidate entities in the KB per alias/synonym
    • min_freq (-f): threshold of number of times an entity should occur in the corpus to be included in the KB
    • min_pair (-c): threshold of number of times an entity+alias combination should occur in the corpus to be included in the KB
  • Further parameters to set:
    • descriptions_from_wikipedia (-wp): whether to parse descriptions from Wikipedia (True) or Wikidata (False)
    • entity_vector_length (-v): length of the pre-trained entity description vectors
    • lang (-la): language for which to fetch Wikidata information (as the dump contains all languages)

Quick testing and rerunning:

  • When trying out the pipeline for a quick test, set limit_prior (-lp), limit_train (-lt) and/or limit_wd (-lw) to read only parts of the dumps instead of everything.
  • If you only want to (re)run certain parts of the pipeline, just remove the corresponding files and they will be recalculated or reparsed.

Step 2: Train an Entity Linking model

Run wikidata_train_entity_linker.py

  • This takes the KB directory produced by Step 1, and trains an Entity Linking model
  • Specify the output directory (-o) in which the final, trained model will be saved
  • You can set the learning parameters for the EL training:
    • epochs (-e): number of training iterations
    • dropout (-p): dropout rate
    • lr (-n): learning rate
    • l2 (-r): L2 regularization
  • Specify the number of training and dev testing articles with train_articles (-t) and dev_articles (-d) respectively
    • If not specified, the full dataset will be processed - this may take a LONG time !
  • Further parameters to set:
    • labels_discard (-l): NER label types to discard during training