Image

Document Classification

Build AI-powered document classification applications in a fraction of the time without hand-labeling data using Snorkel Flow.

Request demo
Image
Image
6 MONTHS

of hand labeled data replaced in 30 minutes using Snorkel

Overview

One Size Fits You, Not All
Achieve greater performance gains by exploiting domain-specific text features of your own data.
Image

Faster, Lower-cost Development

Use programmatic labeling to develop high-quality AI applications in hours instead of spending weeks or months on expensive hand-labeling.

Image

Higher-accuracy Models

Iterate on your application, using a closed-loop approach with intermediate results and analysis at every step to zero in on errors.

Image

Flexible Integrations

Easily integrate labeling, training and analysis pipelines defined over diverse input types–text, PDF, HTML, and more–with downstream applications using APIs or a Python SDK.

Image

Easier SME Collaboration

Build complex classification apps intuitively while preserving natural information about data taxonomies with subject matter expert (SME) collaboration.

Use Cases

Explore Enterprise Solutions For Classification

FINANCIAL SERVICES

Contract Intelligence
Banks can classify contracts by terms and conditions to smoothly ensure regulatory compliance.

TELECOM & CYBER

Customer Segmentation
Telecom organizations can classify customer usage documents to target promotional offers.

HEALTHCARE

Clinical Trial Matching
Biotech organizations can classify patient records to identify actionable clinical trial candidates.

INSURANCE

Risk Classification
Insurance underwriters can classify policy documents by behavioral or occupational variables to assess risk.

SOFTWARE

Email Filtering and Routing
Software companies can classify emails to remove spam and route queries to the correct channels.

RETAIL

Social Media Analytics
Retailers can classify customer reviews to analyze and understand shopping behaviors.

FINANCIAL SERVICES

Credit Decisions
Banks can classify client documents by credit-worthiness, streamlining the credit approval process.

HEALTHCARE

Medical Literature Classification
Healthcare providers can classify medical papers by topic to improve research access.

Case Study

Image

Google used Snorkel to replace 100K+ hand-annotated labels in critical ML pipelines for text classification.

Problem

Content, product, and event classification problems change too fast to hand-label, even with significant annotation budget.

Solution

Google deployed early versions of Snorkel's core technology with three high-impact teams, repurposing many resources as labeling functions.

Result

Hours of labeling function development replaced 10-100K+ hand labels, significantly impacting the bottom line and accelerating of ML adoption.

6 MONTHS

of hand-labeling data replaced in 30 mins

52%

performance improvement

100K+

hand labels replaced with
programmatic approach

How Snorkel Flow Works

Customized AI Apps for Classification
Snorkel Flow is an end-to-end ML platform that makes AI-powered document classification practical and efficient. Create labeling functions to programmatically label and manage training data, then train state-of-the-art machine learning models using your own data. Analyze errors using guided tools and systematically iterate until you achieve deployment-ready performance. Deploy your custom classification application as a real-time or batch API or Python SDK with just one click.

An End-to-end ML Platform

Designed for Collaboration

Image

Data Scientist Friendly

  • Integrated Jupyter notebooks
  • Instant analysis tools
  • Ready-to-use models
Image

Domain Expert Friendly

  • Intuitive, no-code UI
  • Rich dashboards and visualizations
  • Full-featured, push-button error analysis
Image

Developer Friendly

  • Platform access via Python SDK
  • Online or batch API deployment
  • Containerized software for cloud or on-premises deployments

Research

Based on Years of Novel Research
Learn more about groundbreaking techniques for machine learning and weak supervision developed by the Snorkel AI team at Stanford AI Lab and beyond.

RESEARCH

Training Complex Models with Multi-Task Weak Supervision

A. Ratner, et al, AAAI 2019

RESEARCH

Train and You’ll Miss It: Interactive Model Iteration with Weak Supervision…

M. Chen, et al, 2020

RESEARCH

The Role of Massively Multi-Task and Weak Supervision in Software 2.0

A. Ratner, et al, CIDR 2019

RESEARCH

Software 2.0 and Snorkel: Going Beyond Hand-Labeled Data

C. Ré, KDD 2018 (invited)

RESEARCH

Snuba: Automating Weak Supervision to Label Training Data

P. Varma and C. Ré, VLDB 2019

RESEARCH

Snorkel: Rapid Training Data Creation With Weak Supervision

A. Ratner, et al. VLDB 2018

RESEARCH

Snorkel MeTaL: Weak Supervision for Multi-Task Learning

A. Ratner, et al, SIGMOD 2018

RESEARCH

Snorkel DryBell: A Case Study in Deploying Weak Supervision at Industrial Scale

S. Bach, et al. SIGMOD 2019

BLOG

Snorkel AI:
Putting Data First in ML Development

Alex Ratner

RESEARCH

Learning Dependency Structures for Weak Supervision Models

P. Varma, et al, ICML 2019

RESEARCH

Fast & Three-rious: Speed Up Weak Supervision with Triplet Methods

D. Fu, et al, ICML 2020

RESEARCH

A Clinical Text Classification Paradigm Using Weak Supervision…

Y. Wang, et al, BCM MIDM 2019

Accelerate your AI application development today

Request Demo