Finance NLP 1.3.0 for Spark NLP has been released!
We are happy to welcome the new 1.3.0 version of Finance NLP, including the following new capabilities.
Spark Ecosystem
Finance NLP has been built on top of Spark NLP, which uses Spark MLLib pipelines. This means, you can have a common pipeline with any component of Spark NLP of Spark MLLib. Also, you combine it with the rest of our licensed libraries, such as Visual NLP, Healthcare NLP or Legal NLP. The library works on the top of Transformers and other Deep Learning architectures, providing state-of-the-art models which can be run on Spark Clusters. Remember, Spark NLP is the only library natively scalable to do parallel computing, so it is Finance NLP.
New Models
Relation Extraction
finre_earning_calls_sm
→ Extracts relations between amounts, counts, percentages, dates and the financial entities extracted with any earning calls NER modelText Classification
Text Classification
finclf_earning_broker_10k
→ This is a Text Cassification model, which can help you identify if a model is anEarning Call
, aBroker Report
, a10K filing
or something else.finclf_sec_filings
→ This model allows you to classify documents among a list of specific US Security Exchange Commission filings, as :10-K
,10-Q
,8-K
,S-8
,3
,4
,Other
.
Named Entity Recognition
finner_german_financial_entities
→ This is a German NER model trained on German Financial Statements, aimed to extract thefinancial_entity
andfinancial_value
entities from the documents.finner_earning_call_specific_sm
→ This is asm
(small) version of a financial NER model trained on Earning Calls transcripts to detect financial entities. This model is calledSpecific
as it has more labels in comparison with aGeneric
version.finner_earning_call_generic_sm
→ This is asm
(small) version of a financial NER model trained on Earning Calls transcripts to detect financial entities . This model is calledGeneric
as it has fewer labels in comparison with theSpecific
version.finner_financial_xlarge
→ This is axl
(extra-large) version of a financial model, trained in a combination of two data sets: Earning Calls and 10K Fillings. The aim of this model is to detect the main pieces of financial information in annual reports of companies, more specifically this model is being trained with 10K filings.finner_10q_xlbr
→ This model is an NER model containing 139 numeric financial entities from different 10Q reports. The tokens being annotated are the amounts, not any other surrounding word, but the context will determine what kind of amount is from the list of the 139 available. This is a large (lg
) model, trained with 200K sentences.
Text Summarization
finsum_news_headers_lg
→This model is a Financial News Summarizer, aimed to extract headers from financial news. This is alg
(large) version.finsum_news_headers_md
→ This model is a Financial News Summarizer, aimed to extract headers from financial news. This is amd
(medium) version.finsum_news_md
→ This model is a Financial News Summarizer, finetuned with a financial dataset (about 25K news).finsum_news_xs
→This model is a Financial News Summarizer, finetuned with a financial dataset (about 4K news).
New Demos
You can find the existing demos on our Demo site, where you will find demos, showcasing some of the models available in Models Hub.
- Financial News Summarization → This demo shows how to extract headers from financial news and summarize financial news.
- Classify Earning Calls, Broker Reports and 10K → This demo shows how to classify financial documents as an Earning Call, a Broker Report, a 10K filing or something else.
- Extract 139 Financial Entities from 10-Q → This demo shows how to extract 139 financial entities on US Security Exchange Commission 10-Q filings.
- Classify Different SEC Filings → This demo showcases how to use pretrained Finance NLP models to classify documents. In this case,
finclf_sec_filings
allows you to differentiate between 10-K, 10-Q, 8-K, 3, 4 and S-8 filings.
Want to see more?
- Check our Models Hub
- Check our Notebooks
- Check our Demos
How to install
!pip install johnsnowlabs
from johnsnowlabs import *
# Before 4.2.3
jsl.install(json_license_path=[your_finance_license_path])
jsl.start(json_license_path=[your_finance_license_path])
# After 4.2.3
nlp.install(json_license_path=[your_finance_license_path])
nlp.start(json_license_path=[your_finance_license_path])
Do you want to request a free trial?
Go to our self-service installation page here and request a trial. Write to support@johnsnowlabs.com if you have enquiries, or find us at our Slack Channel (#finance)