Finance NLP 1.2.0 for Spark NLP has been released!
We are happy to welcome the new 1.2.0 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 Legal NLP.
New Models
Relation extraction
finre_work_experience_md→ This is amd(medium) version of the finre_work_experience model, trained with more data and with unidirectional relation extractions, meaning now the direction of the arrow matters: it goes from the source (chunk1) to the target (chunk2).
finre_acquisitions_subsidiaries_md→ This model is amdmodel of finre_acquisitions_subsidiaries, meaning that the directions in the relations are meaningful:chunk1is the source of the relation,chunk2is the target.
finre_financial_small→ This model extracts relations between amounts, counts, percentages, dates and the financial entities extracted with one of these models:finner_financial_smallfinner_financial_mediumfinner_financial_large.
Text Classification
finclf_indian_news_sentiment→ This is a small version of the Indian News Sentiment Analysis Text Classifier, which will retrieve if a text is either expression of a Positive Emotion or a Negative one.finclf_indian_news_sentiment_medium→ This is a medium version of the Indian News Sentiment Analysis Text Classifier, meaning this model is a more accurate and will retrieve if a text is either expression of a Positive Emotion or a Negative one.finclf_acquisitions_item→ This model is a Binary Classifier (True, False) for theacquisitionsitem type of 10K Annual Reports.finclf_work_experience_item→ This model is a Binary Classifier (True, False) for thework_experienceitem type of 10K Annual Reports.finclf_auditor_sentiment_analysis→ This is a Sentiment Analysis model which retrieves 3 sentiments (positive,negativeorneutral) from the Auditors' comments.
Named Entity Recognition
finner_sec_dates→ This NER model is trained on SEC documents and empowered with OntoNotes 2022, to extract DATES. This model is light but very accurate.
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 Relation Extraction on 10K filings → This model extracts relations between amounts, counts, percentages, dates and the financial entities extracted with
finner_financialmodels.
Solution Accelerator — Updated!
A Solution Accelerator is a ready-to-use series of notebooks, available and ready to spin up inside Databricks. The final aim of this accelerator is to help you analyze companies information.
All of that information is processed and stores in form of a graph…
The Solution Accelerator is now updated with new and better models. To top it off, a new End to End example using a Securities Exchange Commission 10K form from one company has been included.
Want to see more?
- Check our Models Hub
- Check our Notebooks
- Check our Demos
How to install
!pip install johnsnowlabsfrom johnsnowlabs import *from johnsnowlabs import *
jsl.install(json_license_path=[your_finance_license_path])
jsl.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)
