Financial Spanish Sentiment Analysis, German Relation Extraction, ESG Solution Accelerator, Chinese Sentence Embeddings, new demos and much more!

Photo by Adeolu Eletu on Unsplash

Finance NLP 1.10 comes with a lot of new capabilities added to the 135+ models and 25+ Language Models already available in previous versions of the library. Let’s take a look at each of them!

Spanish Financial Sentiment Analysis

We have participated in the CodeLab competition for Financial NER and Sentiment Analysis on Spanish texts, training models for the following two tasks:

1. Target detection. The identification of the economic target of the headline is hindered by the reduced length of the text and the linguistic features of newspaper headlines.
2. Multi-dimension sentiment classification. As opposed to traditional multi-target tasks in which multiple targets are identified within the scope of each individual processed text, here each news headline refers to a single target entity, but the stances of other economic agents (companies and consumers) are also considered.

As a result, 1 NER model and 3 classifiers (NER target sentiment, consumer sentiment and company sentiment) have been published in our Models Hub repo.

Financial Chinese Sentence Embeddings

Bert and DistilBert Sentence Embeddings provide you with numerical representations (embeddings) of sentences in context. This allows you to calculate the similarity between different financial texts, train classifiers, and cluster your texts. Example of cosine similarity of 8千日利息400元?

Augmented Broker Reports NER

Our Broker Reports model has been augmented with more data.

New demos: Responsibility Reports and QA

In our demo section, you will find three new demos:

1. Responsibility Reports NER

2. Understanding Entities in Context: Detecting if an amount is mentioned to be increased or decreased.

Amounts increasing

Amounts decreasing

3. Financial Question Answering

4. Financial Table Question Answering.

German NER and Relation Extraction

Detect financial values and financial entities in German Financial Reports.

Also, use Relation Extraction to link those values to their related entities.

Solution Accelerator: Responsibility Reports

A series of notebooks (also known as solution accelerator)have been published here to carry out a series of NLP tasks regarding Responsibility Reports (RR).

• Visual NLP to extract text from PDF.

• Text Classification models about ESG (Environment, Social, Governance) with 20+ classes.

• Named Entity Recognition on RR

• Table detection and extraction

• Table Question Answering

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 135 models, including Classification, NER, Relation Extraction, Similarity Search, Summarization, Sentiment Analysis, Question Answering, etc. and 25+ 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()