We are happy to welcome the new 1.4.0 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

Named Entity Recognition
Demo for āfinner_contraliability"
finner_contraliability
Ā ā This is a financial model to detectĀLIABILITY
Ā andĀCONTRA_LIABILITY
Ā mentioned in texts.
–Ā CONTRA_LIABILITY: Negative liability account that offsets the liability account (e.g. paying a debt)
–Ā LIABILITY: Current or Long-Term Liability (not from stockholders)
Improved NER ModelsĀ :Ā We have an improved version of some NER models, including:
finner_earning_calls_generic_md
:Ā This is aĀ md
(medium) version of a financial model trained on Earning Calls transcripts to detect financial entities (NER model). This model is calledĀ Generic
Ā as it has fewer labels in comparison with theĀ Specific
version.
We have addedĀ 12Ā new models having 12 entitiees each which have been trained onĀ 10QĀ reports. These models are a subset of theĀ finner_10q_xlbr
Ā which contains a total ofĀ 139Ā entities.
finner_10q_xlbr_md_subset1
Ā ,Ā finner_10q_xlbr_md_subset2
Ā ,Ā finner_10q_xlbr_md_subset3
Ā ,Ā finner_10q_xlbr_md_subset4
Ā ,Ā finner_10q_xlbr_md_subset5
Ā ,Ā finner_10q_xlbr_md_subset6
Ā ,Ā finner_10q_xlbr_md_subset7
Ā ,Ā finner_10q_xlbr_md_subset8
,Ā finner_10q_xlbr_md_subset9
Ā ,Ā finner_10q_xlbr_md_subset10
Ā ,Ā finner_10q_xlbr_md_subset11
Ā ,Ā finner_10q_xlbr_md_subset12
New Sentence Embeddings
We have released new Chinese and English Bert Sentence embeddings based on Finance Transformers.
sbert_chinese_qmc_finance_v1
Ā ,Ā sbert_chinese_qmc_finance_v1_distill
Ā ,Ā sbert_setfit_finetuned_financial_text_classification
Financial Solution Accelerator
The notebooks for theĀ Companyās EcosystemĀ Graph solution accelerator have been revamped and renewed, now available atĀ https://github.com/JohnSnowLabs/spark-nlp-workshop/tree/master/tutorials/Certification_Trainings_JSL/Finance/databricks_solutions_accelerators/company_ecosystem_graphĀ and ready to use withĀ johnsnowlabs>=4.2.3
in Databricks through Partner Connect!
Docker Webapps to check Finance Zero-shot NER
Do you want to check Zero-shot FinanceĀ NER? Use our dockerized webapps for streamlit or flask+jinja2 and learn about prompt engineering, while you speed up the prototyping of your NER models without any training data. Available atĀ https://github.com/JohnSnowLabs/spark-nlp-workshop/tree/master/tutorials/Certification_Trainings_JSL/Finance/platforms/docker
Want to see more?
- Check ourĀ Models Hub
- Check ourĀ Notebooks
- Check ourĀ 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 get certified in Finance NLP?
We will carry out a Certification training session of 4 hours in Jan, 2023. If you are interested, please check the dates and register hereĀ https://www.johnsnowlabs.com/spark-nlp-training/