John Snow Labs Finance NLP 1.14 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!
New Financial Alpaca-based QA model
We have used the Financial Alpaca dataset to train a Flan-T5 models for specific financial question-answering without a given context.
FIQA-based QA model
Similarly, we used the FIQA dataset to train another Flan-T5 model, also for financial question-answering. The model is able to answer questions as queries without a given answer. This includes questions and queries:
LLM demos
A new demo has been released showcasing how to use Flan-T5 models, finetuned on legal texts to carry out summarization, text generation and question answering.
Demo available here.
New Financial Sentiment Models on Tweets and News
Three models have been created, using Financial Bert, to understand sentiments in financial tweets and news.
New Demo for Visual NER
A new demo combining Visual NLP and Finance NLP to carry our Visual Name Entity Recognition on 10K Filings is available here.
Visual NER is carried out using pixel features, not text.
Fancy trying?
We’ve got 30-days free licenses for NLP for financial services 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 foger 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()