Description
This model helps you retrieve the TICKER of a company using a previously detected ORG entity with NER.
It also retrieves the normalized company name as per Wikidata, which can be retrieved from aux_label column in metadata.
Predicted Entities
How to use
documentAssembler = nlp.DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("ner_chunk")
embeddings = nlp.UniversalSentenceEncoder.pretrained("tfhub_use", "en") \
.setInputCols("ner_chunk") \
.setOutputCol("sentence_embeddings")
resolver = finance.SentenceEntityResolverModel.pretrained("finel_wiki_parentorgs_tickers", "en", "finance/models")\
.setInputCols(["sentence_embeddings"]) \
.setOutputCol("normalized_name")\
.setDistanceFunction("EUCLIDEAN")
pipelineModel = nlp.Pipeline(
stages = [
documentAssembler,
embeddings,
resolver
])
lp = nlp.LightPipeline(pipelineModel)
test_pred = lp.fullAnnotate('Alphabet Incorporated')
print(test_pred[0]['normalized_name'][0].result)
print(test_pred[0]['normalized_name'][0].metadata['all_k_aux_labels'].split(':::')[0])
Results
GOOGL
Aux data: Alphabet Inc.
Model Information
| Model Name: | finel_wiki_parentorgs_ticker |
| Compatibility: | Finance NLP 1.0.0+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [sentence_embeddings] |
| Output Labels: | [original_company_name] |
| Language: | en |
| Size: | 2.8 MB |
| Case sensitive: | false |
References
Wikipedia dump about company subsidiaries