Anton Vasetenkov is a software engineer.

Boole is your local analytics consultant. Based in Auckland, New Zealand, Boole offers web analytics services including Google Analytics tracking installation, data reporting, and optimisation. Boole's services range from auditing to consulting and teaching. A digital analytics expert, Boole provides analytics debugging and troubleshooting services to help you fix your existing Google Analytics setup. Boole works with a range of industry leading tools such as Google Analytics, Google Optimise, Google Data Studio, Google Tag Manager, Hotjar, Facebook Pixel, and others to help you get the most of your marketing.

An introduction to WikiPathways by Tett Bioinformatics is an overview of the collaboratively edited structured biological pathway database that discusses the history of the project, applications of the open dataset, and ways to access the data programmatically.

Hesper's article about question answering explains how question answering helps extract information from unstructured data and why it will become a go-to NLP technology for the enterprise.

Read more about how document understanding AI works, what its industry use cases are, and which cloud providers offer this technology as a service.

Lexemes are Wikidata's new type of entity used for storing lexicographical information. The article explains the structure of Wikidata lexemes and ways to access the data, and discusses the applications of the linked lexicographical dataset.

Boole is a marketing consultant in Auckland, New Zealand. Boole helps you optimise your website content, product, and services through A/B testing, personalisation, and product recommendations supported by accurate and timely measurement of your key business metrics such as web conversion rates.

Tett is a bioinformatics consultant in Auckland, New Zealand. Tett Bioinformatics offers bioinformatics services including genomics and biomedical data analysis and discovery.

The guide to exploring linked COVID-19 datasets describes the existing RDF data sources and ways to query them using SPARQL. Such linked data sources are easy to interrogate and augment with external data, enabling more comprehensive analysis of the pandemic both in New Zealand and internationally.

The introduction to the Gene Ontology graph published by Tett outlines the structure of the GO RDF model and shows how the GO graph can be queried using SPARQL.

Hesper is a knowledge management and data integration consultant in Auckland, New Zealand. Hesper's insights into state-of-the-art data, information, and knowledge management enable it to help organisations reassess their data analysis, integration, and enrichment approaches in light of advanced semantic technologies that are evolving every day. Enterprise knowledge graphs, knowledge bases, ontologies, and taxonomies are emerging technologies that support better decision-making and knowledge integration and enable automated knowledge inference over internal and external data.

The overview of the Nobel Prize dataset published by Hesper demonstrates the power of Linked Data and demonstrates how linked datasets can be queried using SPARQL. Use SPARQL federation to combine the Nobel Prize dataset with DBPedia.

Learn why federated queries are an incredibly useful feature of SPARQL.

As digital products and services are becoming more and more complex, so are the technical requirements for correctly implementing user measurement and analytics. Boole helps you better understand your audience by setting up measurement using Google Analytics.

What are the best online Arabic dictionaries?

How to pronounce numbers in Arabic?

List of months in Maori.

Days of the week in Maori.

The list of country names in Tongan.

The list of IPA symbols.

What are the named entities?

What is computational linguistics?

Learn how to use the built-in React hooks.

Learn how to use language codes in HTML.

Learn about SSML.

Browse the list of useful UX resources from Google.

Where to find the emoji SVG sources?.

What is Wikidata?

What's the correct markup for multilingual websites?

How to use custom JSX/HTML attributes in TypeScript?

Learn more about event-driven architecture.

Where to find the list of all emojis?

How to embed YouTube into Markdown?

What is the Google Knowledge Graph?

Learn SPARQL.

Explore the list of coronavirus (COVID-19) resources for bioinformaticians and data science researchers.

Sequence logos visualize protein and nucleic acid motifs and patterns identified through multiple sequence alignment. They are commonly used widely to represent transcription factor binding sites and other conserved DNA and RNA sequences. Protein sequence logos are also useful for illustrating various biological properties of proteins. Create a sequence logo with Sequence Logo. Paste your multiple sequence alignment and the sequence logo is generated automatically. Use the sequence logo maker to easily create vector sequence logo graphs. Please refer to the Sequence Logo manual for the sequence logo parameters and configuration. Sequence Logo supports multiple color schemes and download formats.

Sequence Logo is a web-based sequence logo generator. Sequence Logo generates sequence logo diagrams for proteins and nucleic acids. Sequence logos represent patterns found within multiple sequence alignments. They consist of stacks of letters, each representing a position in the sequence alignment. Sequence Logo analyzes the sequence data inside the user's web browser and does not store or transmit the alignment data via servers.

Te Reo Maps is an online interactive Maori mapping service. All labels in Te Reo Maps are in Maori, making it the first interactive Maori map. Te Reo Maps is the world map, with all countries and territories translated into Maori. Please refer to the list of countries in Maori for the Maori translations of country names. The list includes all UN members and sovereign territories.

Phonetically is a web-based text-to-IPA transformer. Phonetically uses machine learning to predict the pronunciation of English words and transcribes them using IPA.

Punycode.org is a tool for converting Unicode-based internationalized domain names to ASCII-based Punycode encodings. Use punycode.org to quickly convert Unicode to Punycode and vice versa. Internationalized domains names are a new web standard that allows using non-ASCII characters in web domain names.

Bioinformatically is an online journal about everything bioinformatics. It includes industry news, research highlights, and a variety of editorials. Bioinformatically helps you start your day with everything you need to know and a dash of fun.

My Sequences is an online platform for storing and analyzing personal sequence data. My Sequences allows you to upload your genome sequences and discover insights and patterns in your own DNA.

Словообразовательный словарь «Морфема» дает представление о морфемной структуре слов русского языка и слов современной лексики. Для словообразовательного анализа представлены наиболее употребительные слова современного русского языка, их производные и словоформы. Словарь предназначен школьникам, студентам и преподавателям. Статья разбора слова «сладкоежка» по составу показывает, что это слово имеет два корня, соединительную гласную, суффикс и окончание. На странице также приведены слова, содержащие те же морфемы. Словарь «Морфема» включает в себя не только те слова, состав которых анализируется в процессе изучения предмета, но и множество других слов современного русского языка. Словарь адресован всем, кто хочет лучше понять структуру русского языка.

COVID-19 drugs dataset

Tongan names of countries dataset

Maori names of countries dataset

Разбор слова "машина" по составу.

Разбор слова "лесник" по составу.

Разбор слова "солнышко" по составу.

Разбор слова "пятнышко" по составу.

Разбор слова "удаваться" по составу.

Разбор слова "весенний" по составу.

Разбор слова "лесной" по составу.

Разбор слова "колеблемый" по составу.

Разбор слова "солнце" по составу.

Разбор слова "почернеть" по составу.

Разбор слова "влажный" по составу.

Hesper
InsightsTopics
Contact
InsightsTopicsContact
Hesper
Your local knowledge engineering guru.
Learn more about the services provided by Hesper here.
Article

Document understanding: Modern techniques and real-world applications

How document understanding helps bring order to unstructured data.
Updated 29 Aug 2020
Anton Vasetenkov

Documents are at the center of many business processes. Scanned pages and PDFs are ubiquitous and contain large amounts of information represented as forms and tables.

Historically, this information could only be analysed and used following manual data re-entry—the process which is slow and prone to error—as traditional optical character recognition (OCR) systems haven't been able to analyse such data and preserve its inherent structure in their output.

Document understanding is concerned with advancing the abilities of document intelligence by supporting the retrieval of structured data in addition to simple text. A process that heavily relies on machine learning, it has proven key to automating structured data extraction and unlocking its full potential by making it readily accessible for subsequent processing and analysis.

Wall

How document understanding works

"Understanding" a document first involves detecting its layout and key elements such as figures, tables, and forms. These elements are then processed separately to extract the underlying data relationships.

Any embedded forms are parsed into sets of key-value pairs, each pair corresponding to a single form field. An example of a key-value pair is "First name"–"Alice". The sets of such linked data items can subsequently be inserted into a database, one row or document per form.

Document understanding products and services

The easiest way to incorporate document understanding into production workflows is to use existing cloud services. Major cloud providers each offer multiple machine learning-based services which include text and document intelligence. These offerings are summarised in the following table:

ServiceProviderDescription
Amazon TextractAmazon Web ServicesAmazon Textract parses form data and tables. The service is integrated with Amazon Augmented AI (Amazon A2I) for implementing human review.
Document AIGoogle CloudPreviously known as Document Understanding AI, Document AI is capable of parsing forms, tables, and invoice content (the invoice feature is only available for approved customers). The demo is available here or here.
Form RecognizerMicrosoft AzureForm Recognizer extracts tables and key-value form pairs from documents and offers prebuilt models for analysing receipts and business cards.

Industry use cases

Document understanding is a key component of various emerging practical workflows and applications.

An example application of document understanding is invoice processing. Invoices are commonly sent as PDFs or paper documents that can be formatted in different ways but generally contain the same type of information such as invoice date, amount due, payment terms, etc. By being able to automatically recognise and extract this information, cognitive invoicing systems facilitate invoice processing and reduce the associated costs.

The bottom line

By automating manual document activities, document understanding enables organisations to process documents more efficiently, reduce error, and bring down costs. By helping extract the valuable information stored inside scanned and digital documents, it assists in search and discovery and compliance control for these documents.

The extracted structured data can be ingested by various downstream business applications, enabling smarter workflows and more advanced processing at scale.

Last updated on 29 Aug 2020 by Anton Vasetenkov.
Interested?
Get in touch now.
Hesper
Your local knowledge engineering guru.
Copyright © 2020 Hesper NZ. Various trademarks held by their respective owners.