Matt Shearer

Resolute Square launches, using Data Graphs as a knowledge graph platform, combining CMS, VOD, DAM, SCV & MDM, complete with powerful APIs.

Resolute Square - launches with our knowledge graph SaaS

We are pleased to announce the launch of Resolute Square
[https://resolutesquare.com/?utm_source=datalanguage&utm_medium=newsPost&utm_campaign=launchPost]
, a pro-democracy media organization using Data Graphs [https://datagraphs.com/] 
to provide its knowledge graph -powered Linked Media Platform.

We will publish more detail about the technology in future posts.

Why did Resolute Square choose Data Graphs?
Firstly, Data Graphs enabled the team to combine CMS, VOD, DAM, SCV, MDM, live
streaming, and a knowledge graph to connect the media, all in one place. This
enabled the project to launch quickly, with an enterprise media publishing
platform, complete with powerful APIs, without the need to integrate 4+ vendor
solutions for this central purpose. Speed to Market!

Secondly, this approach enables the Resolute Square team to interlink its media
in order to deliver rich user experiences, and to innovate and pivot rapidly on
an API-first platform. This kind of capability is not available anywhere else in
the market in an integrated SaaS; projects normally need to pin together several
services to achieve this. 

The Knowledge Graph combines Single Customer View with Single Subject View
The domain model joins Creative Works with People, Places, Organisations, and
the Single Customer View "User" model.Another innovation in this project - Video
Streaming
The Resolute Square platform also includes an innovative ultra-low-latency
participatory live video streaming experience, provided by our friends at 
Perfogram
[https://perfogram.com/?utm_source=datalanguage&utm_medium=newsPost&utm_campaign=launchPost]
.

More soon!

Resolute Square Launches, powered by Data Graphs for speed to market

This video was aired on 6th May at the Knowledge Graph Conference 2022 in NYC, as part of the "Knowledge Graph Tools Track".

The 13-minute knowledge graph: Netflix, Disney, Amazon, Hulu

This video was aired today at the Knowledge Graph Conference 2022 in NYC, as
part of the "Tools Track".

This video was aired live at KGC2022We showed participants how they can create a
Knowledge Graph in 13 minutes using open Netflix, Disney+, AmazonPrimeVideo, and
Hulu data from Kaggle.

It ends with a graph path analysis of how Kevin Bacon connects with Sandra Oh,
via shows and casts, using the graph that we implemented in Data Graphs in 13
minutes.

NB - we had made some careful model design and data preparation before setting
up the knowledge graph.

We took our Knowledge Graphs as a Service product "Data Graphs" to The Knowledge Graphs Conference 2022, loaded with Netflix, AmazonPrimeVideo, Hulu and Disney+ data.

Knowledge Graph Conference 2022

The 13-minute knowledge graph, with Netflix, Disney+, AmazonPrimeVideo, and Hulu data

Find out about our feature at KGC2022, and explore this Netflix, Hulu, and Amazon Prime knowledge graph, using our product "Data Graphs".

Data Graphs at the Knowledge Graph Conference 2022

We've launched a read-only version of Data Graphs for participants at the
Knowledge Graph Conference 2022 to have a go, hands-on.

Data Graphs is our Knowledge Graphs as a Service product. It is used by global
brands to provide a knowledge graph platform to accelerate product
time-to-value.

Lowering the barrier to entry for Knowledge Graph Platforms
Often knowledge graphs are seen as a high-cost and high-risk strategy that only
the largest of companies can implement, over a very long time. 

With Data Graphs, we've ensured that businesses can see value rapidly.
Specifically, this means speeding up the ability to do proof of concepts, and
simple but informative demos that allow organizations to realise early value at
low cost and low risk. Here's an example of one of those demos right now.

13 mins to set up:
Netflix, Disney+, AmazonPrime, and Hulu
When developing Data Graphs, we wanted to make the setup and creation of a
knowledge graph, simple and quick. 

This video, prepared for KGC2022, shows how we created a knowledge graph,
complete with secure API and powerful UI tools, ready for production, in 13
minutes:

Try it yourself! - play with the Data Graphs demo here
[https://media-graph.datagraphs.io/media-demo/_all/concepts/?q=&pn=1&ps=15&sf=_label&sd=asc&layout=list&viewport=s000000000,1&utm_source=website&utm_medium=kgc-post&utm_campaign=faceted-search]
This demo version was created using Netflix, Disney+, AmazonPrime, and Hulu
data, and gives you a good view of just some of the key Data Graphs features.

1. Create your Domain Model for your Knowledge Graph
After you have designed and created your domain model with the business entities
and the relationships that link them together, Data Graphs generates a visual
representation of the model so that you can see clearly how the knowledge of
your business interconnects. 

Check out the Domain Model for Shows, Cast, Genres, Ratings here
[https://media-graph.datagraphs.io/media-demo/_domain-model/?utm_source=website&utm_medium=kgc-post&utm_campaign=domain-model]
.

2. Use our powerful Faceted Search over your knowledge graph
The search capabilities of Data Graphs are stellar and allow you to find and
explore your data precisely and most importantly, quickly. With the Advanced
Search feature, you can build complex queries by chaining and grouping a series
of boolean and numeric expressions, to pinpoint the targets of your search. 

Test the search capabilities of Data Graphs here, on 115k concepts including
shows, cast, directors, genres, countries, and more
[https://media-graph.datagraphs.io/media-demo/_all/concepts/?utm_source=website&utm_medium=kgc-post&utm_campaign=faceted_search]
.

As well as an intuitive visual search tool, all the Data Graphs search features
are available via API so you can integrate them with your business systems and
apps.

Explore the Data Graphs API here [https://support.datagraphs.io/].

3. Use the Graph Explorer to visualise your knowledge graph
The graph explorer is one of the star features of Data Graphs. You can now
visualise your knowledge graph in an interactive representation of your data,
that you can then explore and dive into, using the nodes. By visualising your
entire knowledge graph, from any concept in your dataset, we open up a wealth of
possibilities for your structured data. 

Interact with the knowledge graph explorer here, starting from the "Stranger
Things" node
[https://media-graph.datagraphs.io/media-demo/shows/concepts/urn:media-demo:TvShow:netflix-s3686/explore/?utm_source=website&utm_medium=kgc-post&utm_campaign=knowledge-graph-explorer]
.

4. Use the Graph Path Analysis to gain insights
Data Graphs lets you visually explore paths between any entities in the graph,
in order to find the shortest paths, and to specify constraints on both nodes
and properties that make up these paths. A key feature of knowledge graphs, this
type of analysis is typically used in compliance, fraud detection, and supply
chain analytics. 

You can try out the graph path analysis here
[https://media-graph.datagraphs.io/media-demo/_all/_graph-search/?utm_source=website&utm_medium=kgc-post&utm_campaign=graph-path-analysis]
.

About the Data Graphs demo
The Data Graphs demo is a read-only view of the full version of Data Graphs
[https://datagraphs.com]. The complete product provides a full suite of tools
for curating, ingesting, editing, and maintaining data in a knowledge graph,
along with APIs for integration of your graph data with apps and business
systems.

About the Media Graph data
The media graph data has been sourced from the open data provided by Netflix,
Hulu, Amazon Prime, and Disney+ via kaggle.com here
[https://www.kaggle.com/datasets/shivamb/netflix-shows]. The data sets from
these 4 publishers have been cleaned, loaded, and linked together in our graph
to join 72k actors and directors across 21k  TV shows and movies, all faceted by
genre, rating, country, and year of production.

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

Data Graphs at The Knowledge Graph Conference 2022

Alexi Buckingham

We are holding a team hack event this week with themes around blockchain, AI,
and knowledge graphs. We're solving some problems, and having fun with new tech.

A "Hack event" is a useful way of rapidly exploring, and testing new ideas. The
basic format uses a framed challenge and a time constraint.  Participants
usually "hack" in teams, and the emphasis is on creating working prototypes to
test hypotheses.

In stark contrast to a formal product delivery process, hack events participants
get to try any route without the need for production-grade code, or the
restriction of "business as usual" concerns. 

More often than not the prototypes created are not "the next unicorn"-type
projects, but this is ok! The point is to explore the problem spaces, try novel
approaches, and test new ideas efficiently. 

The ideas are tested in the context of our products, and concepts may make it
into our core product set.

Data Language Hack Event

Fabio Colasanti

We have recently completed some new "Inline Entity Extraction" benchmarks. This
is a sophisticated "Named Entity Recognition" (NER) product that we launched as
part of our Text AI Services suite in 2020
[https://datalanguage.com/news/inline-entity-extraction-text-ai-ner]. It is
optimized for Knowledge Graph platforms in high-value knowledge organizations.
It identifies entities inline within text media and attributes rich metadata.

The Problem: Automated Tagging in Custom Domains
Our customers are high-value media publishers, knowledge organizations, and DaaS
providers. 

 * A huge portion of their business asset value is locked in their unstructured
   mixed media assets.
 * To liberate this value, accurate inline text classification of 100s of 1,000s
   of entities is required to enable structured connection with bespoke
   information architecture models and/or knowledge graphs.
 * Generic off-the-shelf NLP SaaS solutions do not recognize these custom
   entities, so a mapping exercise is required, and is often a too low
   resolution to provide value.
 * Many NLP solutions do not provide the rich, domain model-aware metadata,
   because they are not trained for the custom domain.
 * Other custom NLP solutions require larger training sets and golden corpora
   that cover the entire entity set.
 * "Build it yourself" becomes very expensive, with a large data scientist and
   engineering overheads, while organizations find themselves re-solving the
   same challenges that we have already solved.
 * "Manage it yourself" has a surprisingly large data science and engineering
   overhead, to overcome production challenges that we have already solved.

Testing methodology
We trained our Inline Entity Extraction SaaS to understand around 180,000
entities from a custom domain.  We then benchmarked it in a controlled
environment where two teams of annotators were asked to annotate 500 documents:-

 * The first team used the old-fashioned method of manually annotating a
   document.
 * The second team moderated the output of the model that had already scanned
   the documents and picked up entities, only needing to confirm or reject
   pre-determined results.

Results: High F1 Score
Here’s how our Data Language Text AI Services
[https://datalanguage.com/products/datalanguageai/text-ai-services] Inline
Entity Extraction SaaS performed:

 * Precision: 0.94
 * Recall: 0.90
 * F1: 0.92

We have proven we can train a highly accurate model, specialized for a custom
domain, that can cope with hundreds of thousands of entities with very
high-performing metrics, using a golden corpus that covers only a small subset
of the entities. 

Achieving such high results on the classification of such a high number of
classes is very rare for a model like this in the wild.

Results: Huge Workflow Efficiency Gains
The findings of this exercise were that the error rate of the team that used the
Data Language AI model to pre-annotate the documents was substantially lower
than the team that worked without the model. 

 * The team using "Data Language AI" demonstrated a 57% drop in error rate.
 * The team using "Data Language AI" demonstrated a 53% increase in annotation
   coverage.

The measurable benefits were clearly efficiency and accuracy and added to the
coverage of entities being substantially larger, it’s clear that using our model
was a great success.

Should we keep Humans in the loop, or not?
We were also analyzing whether there is benefit in keeping humans in the loop
and this result proved surprising. While it was clear that helping humans out in
entity extractions tasks by pre-running the content through a model could
significantly assist their operation, we actually found that the error rate of
the model was actually slightly higher when humans were involved than when the
results were totally automated. In this case, humans reviewing results actually
makes things slightly worse!

There are some cases where perfect results are not mission-critical - e.g.
upstream automated tagging to simplify downstream workflow, where "the machines
do the heavy lifting". In these cases a certain amount of error is acceptable
and a totally automated process will work. 

In other cases, where errors are less acceptable, the confidence and evidence
metadata in our SaaS can be used to allocate "less certain" predictions to SMEs
and expert analysts for decisions and feedback loop optimizations.

Comparison to other Text Analytics NER Approaches
So what does our competition offer to compete with our results in the Named
Entity Recognition (NER) space? 

Well, it’s difficult to compare apples to apples in this scenario, as our
competitors suffer from the same problem outlined above: Complex custom domains
with small training corpora.

This is the exact advantage of our SaaS that these benchmarks emphasize. 

To put these results into the context of standardized testing of NER performance
elsewhere in the wider world and industry, one usually finds that most tests of
F1 approach the value of 1, only where these models work by identifying a small
handful of classes. Have a look - you will likely see "People, Places,
Organizations, Events"... the usual suspects, and this problem itself has been
solved daily for the last 12 years by almost every computer science student.

The Benefits of Data Language Text AI Services
The fact that our model can cope with a far greater number of classes than most
other providers, and still see such impressive results, is a strong
differentiator.

Another advantage of our Data Language AI Services
[https://datalanguage.com/products/datalanguageai] that we offer is that they
work out of the box at scale for your production platforms.

Our Inline Entity Extraction SaaS comes with all these benefits immediately: 

 * Ability to classify text content to 100s of 1,000s of entities in a custom
   domain.
 * A rich API for interacting with the machine learning service metadata.
 * Automatic management of machine learning model ‘fallout’.
 * Self-optimisation of the machine learning models, on the fly.
 * Capability to cope with an extremely high number of entities.
 * The ability to scale up indefinitely.
 * Production-ready engineering, out of the box.

All the engineering is done, and the security & maintenance are on us!

AI Relationship Extraction for Knowledge Graph Platforms
Later in 2022, we will launch a new commercial Knowledge Graph Relationship
Extraction service as part of Text AI Services - early testing has impressive
benchmarks for high-value knowledge organizations. More to come soon.

For more information on Data Language AI Services, check out the links below.

Data Langauge AI [https://datalanguage.com/products/datalanguageai] | Text AI
Services [https://datalanguage.com/lp/text-ai-services]

New Benchmarks from our Named Entity Recognition (NER) Text AI SaaS Product

After a long history of working together on industry standards, Data Language
has become an official member of the IPTC.

The IPTC is the global standards body for news & media. They provide the
technical foundation for the news ecosystem and involved in setting schemas or
models for the exchange of content in news media. For example, this could be
deciding how the wires are delivered, working on metadata values, controlled
lists of values, and many other functions.

15 Years of Collaboration
Collectively at Data Language we've been working with IPTC on their standards
for the last 15 years, and have been actively involved at many stages. We were
involved in rNews [https://iptc.org/standards/rnews/] which was the schema.org
for news standards, and more recently we've been contributing to their sports
models. Silver Oliver, Data Language's Head of Information Architecture, has
been an active member of the sports model working group, developing those models
to discover what the next generation might be. 

Metadata Innovation in the UK publishing industry
So why did we decide to formalise our involvement with the IPTC? 

Their work is highly valuable in the industry and we want to solidify our
contribution to the innovation, maintenance, support and development of their
standards. We want to help define standards from a Data Language point of view,
and with that be able to encourage the adoption of those standards. As we are
one of the leading agencies supporting metadata efforts in the UK publishing
industry, and given our client expertise, this new relationship with the IPTC is
a great fit.

The opportunity to show our knowledge graph product Data Graphs
[https://datagraphs.com] as an example of good industry standards to other
members of the IPTC is another reason why we wanted to partner even more closely
with them. Having the prestige and quality reputation of the IPTC associated
with Data Language and our push to deliver brilliant knowledge graphs offers
great benefits. We are also always looking at new patterns and tooling in this
space so this membership is an opportunity to validate some of our thinking and
our toolsets against what the IPTC is identifying as the direction that they
think the industry should be going. It's  a really positive way for us to keep
in touch with how the industry itself talks about its needs and what trends are
likely to arise.

Find out more at the links below:

IPTC [https://iptc.org/]| Data Graphs [https://datagraphs.com/] | Knowledge
Graph Engineering [https://datalanguage.com/knowledge-graph-engineering]

Data Language Joins the IPTC

Paul Wilton

Janes is the latest in a group of high-value, knowledge-driven organisations to
develop their information backbone using rapid innovation in data management
with Data Language.

18th November 2021, London:  Data Language, the data innovation consultancy and
solution provider, today announces it is supporting the interconnection of Janes
120+ years of open-source defence intelligence to create Janes Intara, which
enables the integration and normalisation of disparate data sources, allowing
Janes customers to exploit all intelligence sources in an actionable, shareable
manner.

Data Language has worked as part of a joint team with Janes data and technology
experts to launch a new knowledge graph platform to power the Janes Intara
solution. The platform creates the foundations for ongoing and rapid innovation
of Janes foundational interconnected intelligence.

Ben Conklin, Chief Product Officer at Janes, comments: 

> “Our partnership with Data Language enabled us to augment our development of
Janes Intara, a solution that interconnects millions of assured data points
across Janes foundational intelligence, delivering contextualised insight to our
customers. Working with Data Language on our Knowledge Graph has been imperative
to accelerating the development of our first generation product, further
supporting our integration into customer workflows worldwide.”
Paul Wilton, CEO, Data Language, adds: 

> “The impact that Knowledge Graph and AI technologies can have on high-value
information organisations is significant in terms of both enterprise efficiency
and rapid innovation, enabling Janes to deliver state-of-the-art intelligence
data capability to their customers. Data Language is a global leader in
Knowledge Graph solution delivery, and we're delighted to be working with Janes
to develop their Intara platform.”
Data Language has unique expertise and years of experience working with large
organisations to devise and develop world-class data management and innovative
data products, including Knowledge Graph and AI-based tools.

> Pleased that our data and technology experts worked with Data Language to build
the knowledge graph for Janes Intara! Learn more here: https://t.co/RhAtUiVNdN 
https://t.co/ecWCtOQgVh

— Janes (@JanesINTEL) November 18, 2021
[https://twitter.com/JanesINTEL/status/1461351890243833859?ref_src=twsrc%5Etfw]
About Data Language

Data Language is a UK-based data innovation consultancy and solution provider
that has worked with organisations such as News UK, Syngenta and Cochrane to
deliver digital transformation solutions using knowledge graphs and AI. Learn
more at www.datalanguage.com [http://www.datalanguage.com/].

About Janes

The Janes stamp of trust means supplying our customers with timely, validated,
unbiased and relevant intelligence in a world crowded with increasingly
unreliable information. With an unmatched legacy of more than 120 years, Janes
has adapted, expanded, and developed its unique tradecraft while transitioning
from a traditional military publisher to the leading global agency for
open-source defence intelligence. Janes Intara interconnects millions of assured
data points across Janes foundational intelligence, with the ability to
integrate and contextualise multiple sources, delivering the single source of
truth. Learn more: www.janes.com/whatwedo

To find out more visir Data Language Knowledge Graphs
[https://datalanguage.com/knowledge-graph-engineering] | Janes Intara
[https://www.janes.com/intara-interconnected-intelligence]

Data Language & Janes: A Knowledge Graph Partnership

Get hands-on and try the Graph Explorer yourself. Explore the data and interconnections, and help everyone understand your knowledge graph.

Graph Explorer - To demonstrate your Knowledge Graph

The Graph Explorer feature on Data Graphs [https://datagraphs.com/] allows you
to navigate through your knowledge graph visually and interact with your data in
a new light. Being able to present your information visually in the Graph
Explorer helps provide the context, meaning, and interconnection of your data,
an essential asset to your digital transformation.

Demonstrate your Knowledge Graph
A clickable graph user interface enables a visual way of explaining how your
knowledge graph can work for your stakeholders and users. This approach enables
a clickable journey around your business data so that it brings the key
information to life. In our experience this approach generates that "lightbulb
moment" that you have been looking for!

Try it yourself on our Media Demo [https://media-graph.datagraphs.io/media-demo]
Click here [https://media-graph.datagraphs.io/media-demo] to try out our Media
Demo, a read-only version of our product made solely for exploration purposes so
that you can try out the amazing capabilities of the product with no strings
attached. This knowledge graph is populated by thousands of data points from
Netflix, Disney, Hulu, and Amazon and has a plethora of features available to
try out including Search
[https://media-graph.datagraphs.io/media-demo/_all/concepts], Advanced Search
[https://media-graph.datagraphs.io/media-demo/_all/concepts?aq=], Path Analysis
[https://media-graph.datagraphs.io/media-demo/_all/_graph-search], and Domain
Model [https://media-graph.datagraphs.io/media-demo/_domain-model].

Kevin Bacon on Graph Explorer
Click here
[https://media-graph.datagraphs.io/media-demo/people/concepts/urn:media-demo:Person:3Vn1Bxu4W6yzLNL54eB4b5/explore] 
to try out the exact same action being completed in the gif below - exploring
the all media data that links to Kevin Bacon... With Graph Explorer you can
navigate visually through his films, the countries of those films, other actors
he's worked with and much more.

[https://media-graph.datagraphs.io/media-demo/people/concepts/urn:media-demo:Person:3Vn1Bxu4W6yzLNL54eB4b5/explore]
What's the shortest path between Sandra Oh and Ricky Gervais?
Click here
[https://media-graph.datagraphs.io/media-demo/_all/_graph-search/?from=Sandra+Oh%28urn%3Amedia-demo%3APerson%3A6XCMzX4fttIARGWlEPynkN%29&to=Ricky+Gervais%28urn%3Amedia-demo%3APerson%3A2AafOAewdEpIBHxVTKAOHg%29&constraints=0%7Bi%5Byear%3Ar%3A1990%3A2020%5D-%3Ecast-%3E*%7D&view=graph?utm_source=socials&utm_medium=twitter&utm_campaign=shortest-path] 
to complete the action below - finding the shortest path between Sandra Oh and
Ricky Gervais, with path constraints on other actors and shows between 1990 and
2020, and then clicking the Graph Explorer button to visualise the path.

[https://media-graph.datagraphs.io/media-demo/_all/_graph-search/?from=Sandra+Oh%28urn%3Amedia-demo%3APerson%3A6XCMzX4fttIARGWlEPynkN%29&to=Ricky+Gervais%28urn%3Amedia-demo%3APerson%3A2AafOAewdEpIBHxVTKAOHg%29&constraints=0%7Bi%5Byear%3Ar%3A1990%3A2020%5D-%3Ecast-%3E*%7D&view=graph?utm_source=socials&utm_medium=twitter&utm_campaign=shortest-path]
And this entire knowledge graph can be created in just 13 minutes in Data
Graphs... Watch this video to find out how.

Find out more about Data Graphs here [https://datagraphs.com/].

Graph Explorer - Demonstrate your Knowledge Graph

Data Language announces promising results from this Innovate UK -funded AI
project, building on their long-running technology partnership with Cochrane. 

Innovate UK Project
Title: “AI Classification of COVID-19 studies to ensure clinical guidance and
healthcare policy is informed by current meta-analysis of all available evidence
”

This Innovate UK grant-funded project ran from August 2020 to April 2021.

Data Language has worked with Cochrane since 2014, designing and delivering a
microservice-based linked data platform that encodes an authoritative knowledge
graph of healthcare clinical evidence. This has included work to refine, iterate
and scale the platform whilst creating a suite of applications to publish
evidence in healthcare as structured data. The platform enabled Cochrane to
rapidly deploy their Covid 19 Study Register in response to the coronavirus
pandemic in 3 weeks last March.

This Innovate UK -funded AI Project has delivered a new capability in Data
Language’s Text AI services to enable automated creation (“clinical coding”) of
PICO Graphs, using values from Cochrane vocabularies and standard medical
vocabularies assigned to Population, Intervention, Comparison and Outcome
structures for clinical analyses.

The specific outcomes from the initial phase of project work can be summarised
as:

 1. We created a working Machine Learning approach.
 2. We have a clear set of next steps.

Following the successful conclusion of the project work to develop the AI
components, the next steps are to focus on key optimizations to move it into
productionization and commercialization. Timeframes are yet TBC.

Results from our Text AI Services Covid-19 Project with Cochrane

Our knowledge graph product Data Graphs [https://datagraphs.com/] has a brand
new feature. You can now view your entire knowledge graph in the 'Domain Model'
view. This allows you to see your data presented as a spider diagram and explore
it interactively by moving each data point to wherever you like. 

Being able to present your data visually is an essential facet in your company's
digitisation journey and this new Data Graphs feature makes this simple.

Find out more about Data Graphs and Data Visualisation here
[https://datagraphs.com/].