John Snow Labs Finance NLP 1.13 comes with a lot of new capabilities added to the 155+ models and 40+ Language Models already available in previous versions of the library. Let’s take a look at each of them!
Multimodal QA with Visual NLP
Spark NLP suite offers a seamless integrations among all the components: Finance NLP, Legal NLP, Clinical NLP and Visual NLP. This allows you to create pipelines and combine use cases and approaches using all the libraries.
In this notebook, we showcase how to apply both Finance NLP and Visual NLP to do:
- Table Detection, Extraction and Table Question Answering (OCR involved);
- Visual Question Answering (no OCR involved).
Suspicious Activity Reports: new notebooks
In our Finance NLP workshop you will find a series of up to 40 notebooks, including one showcasing capabilities on SAR (Suspicious Activity Reports).
More specifically, this notebook showcases OCR (with Visual NLP) and SAR NER included in Finance NLP. There is also a databricks version here.
Improved Responsibility Reports NER
Our RR (Responsibility Reports) RR got an additional round of annotations and consistency checks, and got improved. Don’t forget to check out the working demo and the Databricks notebooks here.
Other improvements
- finner_deid(Financial Deidentification model)
- finpipe_deid(Financial Deidentification pipeline, including the previous models and up to 10 more to improve the recall).
Fancy trying?
We’ve got 30-days free licenses for you with technical support from our financial team of technical and SME. This trial includes complete access to more than 150 models, including Classification, NER, Relation Extraction, Similarity Search, Summarization, Sentiment Analysis, Question Answering, etc. and 50+ financial language models.
Just go to https://www.johnsnowlabs.com/install/ and follow the instructions!
Don’t forget to check our notebooks and demos.
How to run
Finance NLP is very easy to run on both clusters and driver-only environments using johnsnowlabs library:
!pip install johnsnowlabs
nlp.install(force_browser=True) nlp.start()
