Edit on GitHub
  • John Snow Labs
  • Jan 13, 2023

Map Company Tickers to Subsidiary Companies (wikipedia, en)

  • subsidiaries
  • companies
  • acquisitions
  • en
  • licensed

Description

This models allows you to, given an extracter TICKER, retrieve all the parent / subsidiary /companies acquired and/or in the same group than it.

Predicted Entities

Copy S3 URI

How to use

documentAssembler = nlp.DocumentAssembler()\
        .setInputCol("text")\
        .setOutputCol("document")
        
sentenceDetector = nlp.SentenceDetector()\
        .setInputCols(["document"])\
        .setOutputCol("sentence")

tokenizer = nlp.Tokenizer()\
        .setInputCols(["sentence"])\
        .setOutputCol("token")

embeddings = nlp.BertEmbeddings.pretrained("bert_embeddings_sec_bert_base","en") \
    .setInputCols(["sentence", "token"]) \
    .setOutputCol("embeddings")

ner_model = finance.NerModel.pretrained("finner_ticker", "en", "finance/models")\
    .setInputCols(["sentence", "token", "embeddings"])\
    .setOutputCol("ner")\

ner_converter = nlp.NerConverter()\
    .setInputCols(["sentence", "token", "ner"])\
    .setOutputCol("ner_chunk")

CM = finance.ChunkMapperModel()\
      .pretrained('finmapper_wikipedia_parentcompanies_ticker','en','finance/models')\
      .setInputCols(["ner_chunk"])\
      .setOutputCol("mappings")

nlpPipeline = nlp.Pipeline(stages=[
        documentAssembler,
        sentenceDetector,
        tokenizer,
        embeddings,
        ner_model,
        ner_converter,
        CM
])

text = ["""ABG is a multinational corporation that is engaged in ..."""]

test_data = spark.createDataFrame([text]).toDF("text")

model = nlpPipeline.fit(test_data)

lp = nlp.LightPipeline(model)
res= model.transform(test_data)

Results

{'mappings': ['ABSA Group Limited',
   'ABSA Group Limited@https://www.wikidata.org/entity/Q58641733',
   'ABSA Group Limited@ABSA Group Limited@en',
   'ABSA Group Limited@https://www.wikidata.org/prop/direct/P749',
   'ABSA Group Limited@is_parent_of',
   'ABSA Group Limited@JOHANNESBURG STOCK EXCHANGE@en',
   'ABSA Group Limited@باركليز@ar',
   'ABSA Group Limited@https://www.wikidata.org/entity/Q245343'],

Model Information

Model Name: finmapper_wikipedia_parentcompanies_ticker
Compatibility: Finance NLP 1.0.0+
License: Licensed
Edition: Official
Input Labels: [ner_chunk]
Output Labels: [mappings]
Language: en
Size: 1.3 MB

References

Wikidata