was successfully added to your cart.

Finance NLP 1.7: Capital Calls, Customer Support, Broker Reports, Chinese Financial NER and more!

We are happy to announce the Finance NLP 1.7.0 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, Finance NLP 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 and inference!
  • Zero-shot Name 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.

Capital Call Notices: NER, Notebook, Demo

Detect financial, contact and additional information on Capital Call Notices.

    • Model: finner_capital_calls
    • Demo
  • Notebook including Knowledge Graph visualization

NER in Finance NLP 1.7

Graph visualization in Finance NLP

Broker Reports Classification

  • By the sentiment of the Broker: positive, negative, neutral . Model finclf_bert_broker_sentiment_analysis
  • By the recommended action: upgrade, maintain, downgrade . Model finclf_bert_broker_recommendation
Metrics for Sentiment Analysis in Finance NLP 1.7

Metrics for Sentiment Analysis

Metrics for Recommendations

Metrics for Recommendations

Customer Support Chat Classifiers

Classifier chat messages from Customer Support using different classifiers, based on Bitext dataset.

Multiclass (1 message = 1 class): finclf_customer_service_category (in uppercase, category of the message) and finclf_customer_service_intent (in lower case, specific action required from the customer)

  • ACCOUNT: create_account, delete_account, edit_account, recover_password, registration_problems, switch_account
  • CANCELLATION_FEE: check_cancellation_fee
  • CONTACT: contact_customer_service, contact_human_agent
  • DELIVERY: delivery_options, delivery_period
  • FEEDBACK: complaint, review
  • INVOICE: check_invoice, get_invoice
  • NEWSLETTER: newsletter_subscription,
  • ORDER: cancel_order, change_order, place_order, track_order
  • PAYMENT: check_payment_methods, payment_issue
  • REFUND: check_refund_policy, get_refund, track_refund
  • SHIPPING_ADDRESS: change_shipping_address, set_up_shipping_address

Multilabel(1 message = N classes): use finmulticlf_customer_service_lin_features to analyze the linguistic features of a message, including:

  • Q — Colloquial variation
  • P — Politeness variation
  • W — Offensive language
  • K — Keyword language
  • B — Basic syntactic structure
  • C — Coordinated syntactic structure
  • I — Interrogative structure
  • M — Morphological variation (plurals, tenses…)
  • L — Lexical variation (synonyms)
  • E — Expanded abbreviations (I’m -> I am, I’d -> I would…)
  • Z — Noise phenomena like spelling or punctuation errors

Financial Chinese NER

Model and demo prepared to showcase the capabilities of NLP for financial services with languages which require Word Segmentation, as Chinese (finner_financial_chinese)

Financial Chinese NER in Finance NLP 1.7

Demo: Wikidata for NER, Relation Extraction, Normalization, Data Augmentation and Assertion Status

Using SparQL we are able to obtain data from Wikidata and integrate it in Finance NLP. With that, our Financial Annotators can annotate and create models to analyze companies financial information and extract NER entities, check if an acquisitions has been partial or total with Assertion Status, and much more!

  • Demo
  • NER Models:finner_wiki_sector, finner_wiki_formername, finner_wiki_founding_dates, finner_wiki_nationality, finner_wiki_stockexchange

  • Chunk Mapping(data completion using Wikidata) — only US companies which are Parent Companies of other s): finmapper_wikipedia_parentcompanies

Chunk mapping in Finance NLP 1.7

Certification Training slides

If you have missed our certification trainings, take a look at our slides about Finance NLP here.

Finance NLP training

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()

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 https://www.johnsnowlabs.com/install/ and follow the instructions!

How useful was this post?

Try Finance NLP

See in action
Our additional expert:
Juan Martinez is a Sr. Data Scientist, working at John Snow Labs since 2021. He graduated from Computer Engineering in 2006, and from that time on, his main focus of activity has been the application of Artificial Intelligence to texts and unstructured data. To better understand the intersection between Language and AI, he complemented his technical background with a Linguistics degree from Moscow Pushkin State Language Institute in 2012 and later on on University of Alcala (2014). He is part of the Healthcare Data Science team at John Snow Labs. His main activities are training and evaluation of Deep Learning, Semantic and Symbolic models within the Healthcare domain, benchmarking, research and team coordination tasks. His other areas of interest are Machine Learning operations and Infrastructure.

Finance NLP 1.6: SEC Schedules, NASDAQ and Wikidata integration, and more!

We are happy to announce the release of Finance NLP 1.6 Finance NLP is a John Snow Lab’s product, launched 2022 to provide...
preloader