Document Classification in an Automated Data Extraction Solution
September 15, 2021
|
5 min
IDP
DATA-EXTRACTION

Document classification starts with identifying the text in a document, tagging it, and categorizing the document based on the insights derived from text classification. In intelligent document processing workflow, supervised and unsupervised - both kinds of ML techniques are used to classify documents automatically. Supervised model works on a trained data set and it is a widely used technique because of the accuracy it is able to produce. Based on the algorithm used, the model may provide the user a confidence score and other related metrics to convey how confident the model is in terms of the accuracy for document classification.

So, what is document classification? Who may find it useful? What are different techniques to perform document classification ? What are the limitations and benefits of different deep learning algorithms and machine learning models used to automate document classification? - All questions answered in this article.

Let’s get right into it:-

Table of Contents:-

Introduction

Document classification enables the user to upload different documents in bulk and classify them into their respective types. It helps ease the processing of different document types and assign them to the right team-member for reviewing, processing, and analysis. Document classification tasks can be a huge bottleneck for publishers, insurance companies, financial institutions, and other businesses that receive a large number of multiple document types to process. Before actually extracting data from these documents and organizing it afterwards, they need to classify these documents into respective categories.

For example, let's say an underwriter receives 3 documents types over an email- driver's license, utility bills, and bank statements. Before they can be processed, these documents need to be classified into their respective categories, streamlined in the processing queue, and assigned to the right team member responsible for it.

Types of document classification methods

There are essentially two approaches that to classify and categorize documents: -

  • Manual Classification
  • Automated Classification

Most companies employ the manual classification approach in their workflow. Smaller organizations with a limited number of documents in their processing queue may manage it in-house, whereas organizations with large numbers of documents may outsource it. Despite taking a great deal of time, manual classification is error-prone, costly, and inefficient.

Manual documents classification suffers from two fatal constraints -

  1. Excessive time consumption - The time required to classify and process a massive heap of documents can be substantial.
  2. Subjectiveness - Humans hold biases and different approaches to reality which can cloud their judgment when classifying documents, leading to subjective and erroneous classification.

It takes about 20-40% of an employee's time to locate a document manually, and another 50% to search for information.

However, using a document processing technology, you can swap out the manual classification process, data capture, and document routing with automation, alleviating the total expenses involved in a traditional document processing workflow.

Auto-classification of documents

The solution to the manual classification is the automatic document classification which is much faster and more accurate. As documents are ingested in an IDP system, they are identified, classified, sorted, split, assembled, and processed as per their document type, which enables you to:-

  • Scan documents without pre-sorting or inserting separator pages.
  • Automatically route documents to the appropriate department as per their content.
  • Auto-categorize single-page and multi-page documents.
  • Mark any documents with erroneous or missing pages.
  • Automate verification of relevant batch documents scanning.
  • Assign classified documents to respective team members.

Document auto-classification steps

In an IDP workflow, irrespective of supervised or unsupervised learning technique adopted, document classification works on 3 levels:-

Level 1 - Identifying the file format

Since IDP solutions deal with multiple document formats, the first step is to determine whether the file is a jpeg/png/pdf/tiff or any other format. Whether the file is scanned or non-scanned pdf is determined at this level.

Level 2 - Identifying the document structure

Based on the structure, documents come in 3 categories:-

  1. Structured documents - These documents have fixed templates, layouts, key-value pairs, and tables. Tax return forms and mortgage applications are the best examples of structured documents.
  2. Semi structured documents - These documents may have a fixed set of key-value pairs and tables but they vary in terms of layouts and templates. They may often have similar information at different places in the different documents. Invoices are the best example of semi structured documents.
  3. Unstructured documents - These documents have no structure at all. There are no key-value pairs, formatting, or tables. Documents are textual in nature and carry information embedded in paragraphs. Contracts are best examples of unstructured documents.

Level 3 - Identifying the document type

Documents are classified into respective categories at this level. This process has certain steps:-

1. Pre-processing

In some IDP workflows, this step comes before identifying the document structure. The aim of this step is to identify/distinguish the text from background. Certain techniques such as binarization, deskewing, and noise reduction are used to improve the quality of the document to be processed.

2. Tagged data set

The quality of the tagged dataset is the most important component of a statistical Natural Language Processing (NLP) classifier. The dataset needs to be large enough and must be of a high-quality so that the model has sufficient information of clear delineation for a document type from others.

3. Classification methods

Classification methods are of two types:-

i) Visual Approach

In this approach, computer vision analyzes the visual structure of the document without reading its text. This approach works well for structured documents, and in some cases for semi-structured documents as well. It works on the idea that different document types have information laid out in a document at definite places and patterns. If the model is able to identify those patterns and distinguish them from the patterns on other document types , it classifies the document accordingly. The advantage of this approach is that it happens during the scanning phase thus saves a lot of time.

ii) Text classification approach

In this approach, OCR reads the text from the documents, classified the text, and moves on to classifying the document based on the information derived. With text classification, text can be analyzed at different levels:-
1. Document level - All the text in a document is read.
2. Paragraph level - Text in a particular paragraph is read.
3. Sentence level - Reads text from a particular sentence.
4. Sub-sentence level - Specific phrases are read.

Different methods may read text on different levels based on the training model adopted. Based on the information retrieved, there are 3 classification models that data scientists use for document classification:-

1. Supervised - In this learning method, the user needs to define a set of tags for different documents. For example, in a document, if ‘invoice number’, ‘vendor’s name’, ‘invoice owner’s name’, ‘purchase order number’ and other related fields are tagged and identified, the document can be classified as invoice.  The accuracy of this model depends on the text fields classified and tagged.

2. Unsupervised  - In this learning method, a set of words/sentences/phrases are grouped together without any prior training. These grouped sets are then used to classify the document type.

3. Rule based - This is similar to supervised learning method, however, no text fields are tagged. Instead linguistic rules and patterns based on morphology, lexis, syntax, semantics, and sentiment analysis are applied and used to automatically tag the text and classify the document.

For example (Invoice Number | Invoice Owner ) -> Invoice

The rule-based machine learning algorithm will classify the document as invoice, if above fields are found.

Some common classification algorithms used in data science are:-

  • Naive Bayes classifier
  • Term frequency-Inverse document frequency (tf-idf)
  • Artificial neural network
  • k-nearest neighbours algorithm

Document auto-classification - Benefits and perks

Document classification transcends beyond algorithmically classifying documents with advanced ML and renders the following perks -

1. Adaptability to highly variable content

With advanced Machine Learning technology and AI augmentation, document categorization automatically categorizes scanned and digital documents as per their content, even when the content is variable.

2. Employee time savings

Automating document classification eliminates the requirement for human intervention and manual classification of documents, which is time-consuming and potentially repetitive.

Implementing auto-classification saves employee time, improves job satisfaction, and alleviates staff turnover rate.

3. Prevent data breaches

Automated document classification helps enterprises efficiently gather and centralize data. This gesture helps identify PII (Personally Identifiable Information), reducing the risk of a data breach.

The classification of sensitive data improves organizations’ ability to evaluate and address sources of PII, delete redundant documents that contain sensitive information, and retain critical PII.

Document classification with Docsumo

Docsumo is a document AI software that facilitates the seamless extraction of data from different document types. The platform enables you to categorize documents into their respective document types, which saves you the trouble of opening individual PDFs or images.

Docsumo comes with a set of pre-trained APIs that deliver staggering accuracies for various document types such as invoices, bank statements, identity verification documents, forms, and more. You can also train it for various other document types as per your business needs besides pre-trained APIs.

Coming to document auto-classification, here is how you can classify different document types in Docsumo:-

Step 1: Open 'API and Services - Visit ‘API and Services’ on Docsumo's interface

API and Services

Step 2: Enable document types - Under 'Actions' enable the document types you wish to categorize. After enabling the required document types, their status type will change from ‘disabled’ to ‘enabled’ for that specific document type.

Enable Document Types

Step 3 - Enable ‘Auto-classification’ - To enable the ‘auto-classification’ feature, make sure that each document type that you’ve selected in the step-2 has been trained against at least 20 documents.

Enable auto-classification

 Step 4: Upload your documents - Go back to the ‘Document Types’ and upload the documents collectively in the auto-classification section.

Step 5: Receive classified document types - Get intelligently classified outputs according to their respective document types, which are visible under ‘Types’.

Auto-assign the categorized documents with Docsumo

If you wish to have different document types evaluated by different team members, you can select the ‘Auto-Assign’ option by following these steps:-

Step 1: Visit 'Document Types' - Navigate to the ‘Document Types’ option.

Step 2: Open Settings - Select the Setting icon for a particular document type.

Setting icon

Step 3: Choose a member - Pick a suitable member from your team from the 'General Settings' option.

Auto assign

After following the above three steps, you can auto-classify different document types and delegate them to individual team members and obtain validation and approval.

Data protection and integration with Docsumo

At Docsumo, we take data protection and security very seriously.  Docsumo is a GDPR compliant and SOC-2 certified company. All requests get transferred over HTTPS only, and data transfer gets encrypted with AES 256. All the stored data on S3 & Mongo dB also gets encrypted.

You remain in power by choosing to delete the data from our servers promptly or periodically after you have completed document processing. You can monitor individuals with access to different data types in your organization via advanced user management.

We realize that no platform exists in a vacuum, which is why we have built our solutions to integrate with other software and solutions. By employing plug-in APIs and out-of-the-box input and output connectors, our platform can conveniently get integrated into any workflow.

If you’re curious about how Docsumo operates and simplifies document processing for different industries, accurately extracts data, and safely stores & organizes it - all that in real time,  schedule a free demo with us. We’d love to hear from you about your business use-case and figure out how we can help!

Is document processing becoming a hindrance to your business growth?
Join Docsumo for recent DocAI trends and automation tips. Docsumo is the Document AI partner to the leading lenders and insurers in the US.


Written by
Pankaj Tripathi
Share this Blog:
A'p
  • I agree and understand that Docsumo may send me marketing communication via email. I may opt out at any time.

Document Classification in an Automated Data Extraction Solution
DATA-EXTRACTION
|
May 14, 2021
|
5 min
Share this article

Blog

Explore more