Bleeding Edge Series: Multi-Doc Summarization

28th November 2017

In our new series, Bleeding Edge, we look at break through technologies within Text Analytics, Machine Learning and Natural Language Processing that are making the transition from academic lab rat to corporate cash cow. We’ll take a deep dive into the different technical approaches, and review some of the commercial applications, and the companies starting…

Extracting Media from HTML

14th November 2017

Over the last decade, there has been a rapid development from static webpages with little interactive content to media-rich and dynamic web pages. This can be attributed to new web technologies that make embedding of multimedia content incredibly simple. For example, adding a video in HTML5 is as easy as wrapping it in <video> tags.…

A Benchmark Comparison Of Content Extraction From HTML Pages

22nd September 2017

Introduction Content extraction is the task of separating boilerplate such as comments, navigation bars, social media links, ads, etc, from the main body of text of an article formatted as HTML. The main content typically accounts for only a small portion of a page’s source code (highlighted in red in the image below). Extraction is…

Summarising lists, a popular web content type.

7th June 2017

  One of the biggest challenges we’re trying to tackle at Skim Technologies is how to extract the most important information from a web page, in order to vastly improve the way people consume information in a mobile first world…  This post details some of the work we’ve been doing to automatically summarise lists. We…

A benchmark comparison of extractive summarisation systems

23rd May 2017

In this post, we report the results of the comparative evaluation of our Skim API against similar commercial and open-source extractive summarisation systems. Results indicate that our summarisation system consistently outperforms the analysed benchmarks, in terms of ROUGE-N.   The Information Age we are living in, fuelled by the advent of the World Wide Web…

Why we’ve changed from Scrum to Kanban…

28th March 2017

In the two short years we’ve been developing software at, we’ve always taken an agile approach to our work. It’s not always been easy, and now more so than ever – like true Agile ninja’s – we’re questioning, testing and improving our processes. There’s a misguided belief among tech startups that the only way…

A brief introduction to summarisation

5th November 2016

Our chief data scientist shares her thoughts on summarisation, by answering some of the most burning questions on this exciting discipline of information management.

What you need to know about Mentorship…

2nd May 2016

In this post I identify the benefits mentorship offers, and why getting a mentor is hard. Furthermore I identify the approach to take to find a mentor, and importantly how to make the mentorship relationship work so as to experience the promised benefits.

Why you should stop running your own node server

4th April 2016

In this post, Florian – our Fullstack developer – reveals why he thinks the future is serverless…

Our mission

Skim’s mission is to empower people to use data more effectively and to demisty artificial intelligence. Rather than holding up the common narrative of machines replacing humans, we see how machines can help humans to have easier lives and better businesses.

Supported by


27 Finsbury Circus 

+44 207 129 7497