Matt Shearer

We work with organisations to deliver their ambitious production AI projects,
and we understand the need for speed, and for managing total cost of ownership.

Avoid getting stuck in "Proof of Concept" phase
In a recent survey of 1,093 industry professionals by Forbes, 64% of respondents
agree that the challenges of implementing AI have been underestimated. 61% of
the same group agree that many AI projects were having trouble getting beyond
Proof of Concept and prototyping stages.

Deliver production value, quickly and early
At Data Language, we have seen all the common issues in the design,
implementation and scaling of AI systems, and we can help you through this
process. We specialise in delivering valuable MVPs quickly and early.

Let's talk
Get in touch with us for a free assessment - we are here to help!

SCOPA

Delivering a Scalable AI MVP

Paul Wilton

Tagmatic was originally designed to meet the challenges of automatic content
tagging in the publishing industry, and is ideally suited to classification and
tagging of news, sport and entertainment content.

Why do publishers tag their content?
Most large publishers need to tag or classify their content for a number of
reasons :

 * to assist internal processes and work-flows
 * to improve search and discovery
 * to provide richer content and user analytics
 * to drive advertising
 * to deliver richer user experiences

Typically tagging is a manual task, integrated into the editorial workflow and
the CMS. Increasingly, publishers are working to automate this process using NLP
and machine learning techniques.

Automated content tagging
Automating content tagging unlocks a lot more value, as the automated-tagging
system can be used to

 * improve tagging efficiency, consistency and quality on the news desks
 * fully-automate tagging of external news feeds
 * unlock value in long-tail content
 * automate tagging of other content around the organisation

For this reasons, publishers are investing large sums and time in building their
own automated tagging systems. However what may seem like a simple problem in
the R&D labs can turn into a much more complex and expensive problem, when put
into production.

How Tagmatic can help
Tagmatic [https://datalanguage.com/tagmatic] is an AI and Machine Learning fully
managed SaaS platform. We built Tagmatic to make it as simple as possible to
integrate automated tagging into your publishing systems, addressing all the key
challenges :

 1. It is incredibly easy to integrate. Send it content to learn. Send it
    content to tag.
 2. It uses your own dictionaries, taxonomies, and classification vocabularies
    out of the box.
 3. The engineering challenge of scaling, retraining, and efficiently
    redeploying the machine learning models is done for you.
 4. It learns on the fly. As new terms arise in news, Tagmatic learns them
    quickly.

Total cost of ownership
Building you own AI based tagging solution is no mean feat. It is not just a
data science problem, but involves software engineering, testers, DevOps,
infrastructure, scaling automation, model deployment automation, continuous
machine learning model training automation, as well as the project management
and business processes that accompany a project of this nature. Both the total
cost of ownership and time-to-deliver is substantial.

With Tagmatic you can be up and running in hours, not months, at a fraction of
the total cost and you can put your data scientists to work on your market
differentiating data outomes instead.

Contact us now for a free trial.

Tagmatic for Publishers

Working with change, not against it
Change happens: markets conditions change; competitors change; supply, demand,
technologies, cultures, people - all change. Successful organisations are those
able to respond to change timely and effectively, turning risk into
opportunity.  For business to implement and execute on an effective technical
strategy, the ability to adapt to new conditions is the key to success.  We
specialise in evolutionary design, a powerful approach to technical strategy
that enables organisations to gain business advantage through fast reaction to
market changes.

Whatever the state and history of your technical function, it should never hold
back your business vision. Technology should enable and exploit opportunities,
not jeopardise your first-mover advantage or get in the way of on your
commercial strategy. If you feel your technical estate is making you miss out on
business opportunities then give us a call. We can help.

How we can help
We have helped customers from start-ups to bluechip multionationals implement
strategies which have delivered ambitious business plans and enabled them to
exploit new commercial opportunities. That ability to innovate and evolve has
been shaped through:

 * A deep, shared understanding of the business domain
 * A dogged commercial focus on core market differentiators
 * Anchoring everything against customer needs
 * Mapping evolutionary trends in the technologies that support those needs
 * Relentless technological focus on simplicity
 * Rigorous technology risk management
 * Lean processes for agile governance

Expert Technical Strategy

Data Language has exceptional experience in the design, implementation and
deployment of knowledge graphs, linked data,  and semantic technologies. We have
been working with graph databases since our inception, when our founders worked
on possibly the UK’s first enterprise scale knowledge graph for BBC News and
Sport. Since then we have helped global organisations such as Cochrane,
Wellcome, and Euromoney implement them too. Our typical approach to implementing
a knowledge graph solution is :

Domain Driven Design
Through collaborative domain modelling exercises, we work with stakeholders to
gain a broad understanding of the target domain, iteratively refining and
validating ontology models to achieve the ideal level of detail to deliver the
best outcomes, business value and utility.

Technical and Data Architecture
Not all graph databases are equal. We are wholly vendor-agnostic, and our deep
experience in designing scalable, maintainable, and evolvable knowledge graph
solutions, means we will always select the right graph technology to deliver
your use-cases. We understand the difference between label-property graphs and
RDF based graph databases. We have a total grasp on the practical and pragmatic
use of semantics and inference to ensure your solution is not over-engineered
but delivers just the right level of complexity to optimise your total cost of
ownership, and ensure your solution can evolve as your business evolves.

Integration - Data and Software Engineering
We can help you integrate the knowledge graph with your business systems and
workflows, either by helping your own software engineering team with querying
the graph using query languages such as SPARQL or Gremlin, through to developing
microservices and web interfaces that encapsulate your target use-cases. We are
skilled at data engineering, and can help you populate your knowledge graph,
transforming and loading your own business data, and linking to or ingesting
open-data as required.

Automation and Deployment
We can work with and guide your own infrastructure team, or take on the task of
engineering, integration and deployment entirely ourselves. We are skilled at
contemporary best practices for deployment of infrastructure in the cloud or
on-prem. Our devops engineers are skilled in the use of infrastructure-as-code
for fully automating the deployment and maintenance of the entire knowledge
graph solution.

Graph databases

Knowledge Graph Engineering

Tolga Ergin

It’s what we do
Building innovative data driven platforms and products is what we do. We are
experts in innovative data driven products and platforms. 

We are world class data and software engineers, and build practical machine
learning and AI solutions that deliver real business value rapidly.

But we don’t just stop at the platform, our talented developers also build
beautiful, accessible data visualisations and user experiences.

How do we do it
Our approach is multi-fold. Tried and tested, and focussed on delivering early
value.

Domain-Driven Design
To build a great product it is critical to understand the domain. We use 
domain-driven design [https://datalanguage.com/domain-driven-design] at the
outset to gain a broad-enough and deep-enough understanding of the problem space
and value-proposition not just to deliver the right solution, but to deliver the
right value too.

Minimum Useful Product
Delivering early value is key. Working with stakeholders and the outputs of
domain-modelling we identify a Minimum Useful Product (MUP), that is both
desirable and viable.

Technical Strategy
We take a practical and pragmatic approach to technical strategy
[https://datalanguage.com/technical-strategy], tailored on business vision,
rigorous risk management, lean processes for agile governance, ultimately
designing technical solutions to support market opportunities.

Iterative Full-Stack Implementation
We build a feature-driven vertical slice through our platform as early as
possible. We automate from the outset using contemporary tooling for continuous
delivery, including infrastructure-as-code, and
test/behavioural-driven-development patterns.
Our data models are maintained and evolved iteratively too, modelling
just-enough to deliver the detail of the evolving-features, while keeping in
mind the big picture domain model. 
By delivering an early vertical-slice, we identify risks and challenges early.
Our vertical-slice is iteratively evolved feature-by-feature to deliver the MUP,
with user and stakeholder feedback at each iteration.

Data Driven Product Innovation

Luminery is a new type of video experience, where users can interact with
moments in video. For Jamie Oliver, this means getting more from each step in a
recipe video, and highlighting products that are used in the video so that
viewers can buy them directly.

This image shows a "Making thyme flavoured oil" video moment, that had an
interaction rate of 62%.From a data sample of 1 month of Luminery Video Moments on Jamie Oliver
[https://datalanguage.com/news/jamie-oliver-christmas-videos-enhanced-with-luminery]
, here are some highlights:

Video Moment Engagement
 * Challenge: Video experiences haven't changed for years. Can we get a new,
   user-centred experience that dramatically improves how viewers use Jamie
   Oliver videos?
 * Solution: Identify steps in the recipe, and the techniques, products and
   ingredients in those steps. Activate the steps as structured "How To" moments
   using Luminery. Add important products so that users can find them directly.
 * Results: 92 new "moment interactions" per 100 video views. 9.3% Interaction
   Rate with HowTo steps (compared to the current ZERO).

Video Marketing Conversion Performance
 * Challenge: Jamie Oliver produces a range of products, and creates incredible
   recipe videos. How do we drive better product sales from these videos?
 * Solution: Identify products in the recipe and activate the moments to help
   users directly reach and buy the products at the right moments using Luminery
   (saving huge conversion fall-off due to searching and uncertainty barriers).
 * Results: 5.4% CTR (clicks as % of video views) generated by the "product
   moments" (compared to 0.5% of standard pre-roll Ads). 9.6% conversion rate at
   the Ecommerce vendor destination for Jamie Oliver products.

What does this tell us?
This demonstrates, again, the benefit of using structured video moments to
activate new value in Video. We've demonstrated new engagement and revenue
-driving opportunities, and a fresh model for video publishing.

Luminery is our state-of-the-art Video Moment SaaS product, enabling Publishers, Brands and Creators to leverage the value of video micro-moments for increased revenue and engagement. Find News and Product Updates about video micro-moments here.

Read about Luminery product updates, new features, News, and Martech blog posts on Video Micro-Moments, contextual commerce, engagement and innovation.

Luminery - News & Product Updates about our Video Moment SaaS

Luminery

Video Moments Stats from Luminery on Jamie Oliver Videos

A knowledge graph is a collation of information and data typically within the domain of your business context. The information is stored in a database, often a graph database such that it can be queried, maintained, and interacted with by humans or machines. We have exceptional experience in the design, implementation and deployment of knowledge graphs. We have been working with graph databases since our inception and have delivered knowledge graphs solutions for global organisations.

We have exceptional experience in the design and implementation of knowledge graphs and have delivered knowledge graphs solutions for global organisations.

Knowledge Graphs - our Work, Features, News and Updates

Knowledge Graphs

How knowledge graph technology is helping Cochrane respond to COVID-19

Silver Oliver

An introductory guide to tagging: Part 3

It has been my experience that many organisations struggle with high quality
tagging. In this post I am going to reflect on some of the causes of this
problem. 

As discussed in earlier posts, the value of tagging is often not properly
understood
[https://datalanguage.com/features/the-importance-of-tagging-when-publishing-to-the-web]
.  Most often it is considered to be there to support keyword search alone.
 Even the taggers themselves are not aware of how the tags are going to be used,
or why they need to be of good quality to add value.

The next issue is around the guidelines given to taggers.  Typically they are
extremely poor, and go along the lines of “tag what the content is about”.  This
question of “what is it about?” is harder than it seems at first glance and not
very helpful. It usually results in a different answer from each tagger.  To get
good quality tagging you need to ask good quality questions.

As the tagging quality goes down, the ability to drive useful features from the
tags also diminishes. This in turn does nothing to reassure people of the
importance of good tags and you end up in a vicious cycle of ever decreasing
quality and value. 

What good guidance on tagging looks like should be the point where Library
Science can come to the rescue.  But the challenge of how to identify the
subject of a work is a surprisingly under represented topic in Library Science
literature. 

Back in the the 1970s, Hutchins observed:

> THE LITERATURE OF INDEXING AND CLASSIFICATION contains remarkably little
discussion of the processes of indexing and classifying...we find very little
about how indexers and classifiers decide what the subject of a document is, how
they decide what it is 'about'.
The concept of 'aboutness' in subject indexing:
[http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.584.8116&rep=rep1&type=pdf] 
 W. J. Hutchins

Little has changed.  Taggers are often told to imagine "how might the user
search for this piece of content" or "take the author's view and characterise
what they are trying to say".  Neither is very useful as a framing question. 

Hutchins, in his paper, tackles this problem and introduces a distinction
between summarisation and aboutness. Summarisation is the representation of the
total subject content of a document and the statements made therein. While
aboutness is about capturing the thing that has been written about.

A very simple example might be a sport story about a player and whether they
will move clubs, their struggles with injury and their performance this year.
Many arguments are developed, making up the narrative of the story.
Summarisation would capture not only the player as a tag but also attempt to
capture something about the claims made about the subject of fitness,
performance and likely future at a club.  On the other hand, aboutness only
attempts to capture the thing being talked about and not what claims are made
about them. In this case just the player.

This distinction is rarely made in tagging guidelines and the tagger is left to
balance the level of summarisation and aboutness on gut feel.

Hutchins goes on to characterise this distinction in another interesting way.
The aboutness represents those things that are expected to already be part of
the readers knowledge. Every piece of content assumes a level of knowledge of
the reader with which the narrative then builds. Summarisation on top of this
attempts to capture what is new and builds on that existing knowledge in the
narrative of the content.  The readers are familiar with the player, but not
about the subtle changes in his fitness and future prospects.

With this in mind, the questions we might ask a tagger to answer are: What is
the thing being talked about? What claims or facts are made about a thing in the
content? What might the reader be presumed to know before reading this?

Whether we choose to do summarisation or capture aboutness is a decision related
to the desired outcome of the system. But we should be clear about which one it
is.

A more recent analysis by Birger Hjorland (The concept of subject in
Information
Science [https://www.emeraldinsight.com/doi/abs/10.1108/eb026895]) revisits the
problem.  He cites many examples of Guidelines expecting taggers to do little
more than perform "mind reading" on prospective future consumers of the content.

Instead, he argues, we must think about tags as a tool in enabling the full
potential of the document within the context of the overarching system.  The
desired outcomes of this system should then dictate the tagging strategies and
guidelines. 

It is this domain and system that must be crystal clear in taggers' minds as
opposed to the idea of aligning subject to a theoretical searcher.  They need to
also understand the value that they are creating and how.

Sadly, this is the opposite of what we see in many tagging tools and guidelines
today.

I would argue that tagging should be a contract between taggers and the system
 much in the way we see in the design of data services
[https://medium.com/@diogo.lucas/https-medium-com-diogo-lucas-contract-breaks-are-kinda-of-deal-breakers-447762de20c4]
.  Tagging guidance needs to be managed with a vision of the desired outcomes
combined with asking clear and simple questions of the taggers. This is as true
for humans as machines.

In summary, tagging outside of libraries and archives is often of poor quality.
Value is rarely understood, content creators are often asked to tag in ways that
are a chore and cognitively awkward. Worst of all, the question of what good
tagging looks like has rarely been asked.

In the next post I will look at some potential solutions to the challenge of
better tagging
[https://datalanguage.com/features/how-to-use-domain-modeling-to-improve-subject-tagging]
.

Part 1: Why the web turned its back on the librarians. And why we need them
back.
[https://datalanguage.com/features/why-the-web-turned-its-back-on-the-librarians]

Part 2: The importance of tagging when publishing on the web
[https://datalanguage.com/features/the-importance-of-tagging-when-publishing-to-the-web]

Part 4: How to use domain modeling to improve subject tagging
[https://datalanguage.com/features/how-to-use-domain-modeling-to-improve-subject-tagging]

Data Language is an industry leader in Information Architecture, ontology design and practical knowledge graph implementation. We use Domain Driven Design practises and user-centred design to focus information and data design on core business needs.

Find Information Architecture news and product innovation updates here, including ontology design, vocabulary management, domain & data modelling and more.

Information Architecture - News, Product Innovation and Technology

Information Architecture

Why good subject tagging is hard

Data Language is trusted by global brands for Digital Transformation products and services. We specialise in information architecture and data strategies, and pride ourselves in our collaborative and supportive approach to delivery with our partners.

Data Language are specialists in Digital Transformation. We are trusted by global brands to deliver data science and information architecture strategy.

Digital Transformation

Our Digital Transformation work

Digital Transformation Blog Posts

News about Digital Transformation