Watch Healthcare NLP Summit 2024. Watch now.
was successfully added to your cart.

Finance NLP: New Relation Extraction Training Template, Fuzzy Search in Chunk Mappers, new Broker Suggestion classifier and more!

We are happy to announce the Finance NLP 1.8.0 is out.

Finance NLP is a John Snow Lab’s product, launched 2022 to provide state-of-the-art, autoscalable, domain-specific NLP on top of Spark.

With more than 125 models, featuring Deep Learning and Transformer-based architectures, NLP Finance includes:

  • Annotators to carry out Name Entity Recognition, Relation Extraction, Assertion Status / Understanding Entities in Context, Data Mapping to external sources, Deidentification, Question Answering, Table Question Answering, Sentiment Analysis, Summarization and much more, both training andinference!
  • Zero-shotName Entity Recognition and Relation extraction;
  • 115+ pretrained Deep Learning / Transformer-based models;
  • Fully integration with Databricks, AWS or Azure;
  • 33+ notebooks and 25+ demos ready to showcase its features.
  • Full integration with NLP Lab (former Annotation Lab) for managing your annotation projects and train your financial models in a zero-code fashion.
  • Compatiblity with Visual NLP, to combine OCR/Visual capabilities, as Signature Extraction, Form Recognition or Table detection, to Finance NLP.

New TF2.X Relation Extraction Template

Train Relation Extraction models, using our implementation of Span-Bert paper for TF2.X, with our new Relation Extraction training template.

This template is adapted and available for Finance NLP here.

Fuzzy Matching in ChunkMappers

We call Chunk Mapping to the ability of mapping NER tags to additional information, available in any data source we may have.

For example, let’s suppose we use an NER model which extracts ORG and we detect Auxilium Pharmaceuticals as NER chunk. We can map that ORG to our SEC Edgar Chunk Mapper to get more information about that company.

Before, ChunkMapping needed to have an exact match to map to additional sources of information, or use Entity Resolution (conversion / normalization) to do a similarity search and find the closest representation of what we extracted (Auxilium Pharmaceuticals) in Edgar (Auxilium Pharmaceuticals Inc.)

Now, we don’t need to worry about doing Entity Resolution: we offer fuzzyMatch in all of our ChunkMappers. This means: if you extract Auxilium Pharmaceuticals and in Edgar Chunk Mapper you have Auxilium Pharmaceuticals, Inc. you will be able to do the match without any issue.

Notebook here.

Broker Suggestions classifier

finclf_bert_broker_reports_suggested_actions: New classifier which detects if a broker suggest any of the following operations on your stock assets: Accumulate, Buy, Hold, Neutral, Reduce, Sell

Identify Partial or Total Acquisitions in texts

finassertiondl_acquisitions: This is an Assertion Status model, able to identify, giving ORG NER entities, if there is a mention of an acquisition. If so, the assertion model will analyze the context and return either TOTAL_ACQUISITION or PARTIAL_ACQUISITION. If the ORGS are not mentioned in any acquisition context, the model will return OTHER

Models fixed

  • finner_orgs_prods_alias: Model to detect Organizations, Products and Aliases on Financial Texts. More data, reduced recall and false positives improving accuracy.

  • finner_headers: Model to detect Headers and Subheaders in financial texts. Reduced recall and false positives improving accuracy.

Accessing Wikidata offline with Chunk Mappers

We have a new notebook which demonstrates how to create dumps of Wikidata, using SparQL, to create a Spark NLP ChunkMapper, and be able to match your NER entities to information from Wikidata for augmentation purposes!

For example, let’s suppose we detect the ORG Lafarge In Wikidata, there is much information about this company, including subsidiaries Lafarge Tarmac, tickers, stock exchanges etc.

The notebook available here will show how to import that data so that you can map Lafarge NER chunk and augment with information from Wikidata:

New notebooks folder

Our notebooks folder with examples about most of the features of Finance NLP is now available here.

How to run

Finance NLP is very easy to run on both clusters and driver-only environments using johnsnowlabs library:

!pip install johnsnowlabs

Fancy trying?

We’ve got 30-days free licenses for you with technical support from our financial team of technical and SME. Just go to and follow the instructions!

Installing Finance, Legal or Clinical NLP with one-liners!

Legal NLP and Finance NLP are built on the top of a new John Snow Labs library, called johnsnowlabs . If you are...