Posts Tagged ‘ibm’

I-Spy (using Watson services from Scratch projects)

Wednesday, February 22nd, 2017

It’s half-term week, so that means more time for geekiness with the kids.

This is something Grace made this week: a game of “I spy” built using Scratch, that uses the Watson Vision Recognition API to let the game dynamically pick objects that it recognises in photos, so you can then make guesses.

Apart from being a fun game to make in it’s own right, I wanted to share why I particularly think it’s useful to be able to use Watson API’s from Scratch projects.

Screen Shot 2017-02-22 at 13.43.53

(more…)

Normalised Discounted Cumulative Gain

Friday, July 15th, 2016

A ramble about accuracy compared with NDCG scores for evaluating effectiveness of information retrieval. It’s an introduction, so if you already know what they are, you can skip this.

A couple of weeks ago, we released a new tool for training the IBM Watson Retrieve and Rank service (a search service that uses machine learning to train it how to sort search results into the best order).

This afternoon, I deployed a collection of small updates to the tool and thought I’d make a few notes about what’s changed.

Most of them are a bunch of incremental updates and minor bug fixes.

For example, support for a wider range of Bluemix environments, support for larger document cluster sizes, displaying the amount of disk space left in a cluster, and so on.

One update in particular I thought was more interesting, and worth explaining.

(more…)

IBM Watson Retrieve and Rank tool

Thursday, June 30th, 2016

A few months ago, I mentioned that I was starting a new project. In this post, I’ll explain what we’ve been working on and what we’re trying to achieve with it.

The project was to build something new: a self-serve web-based tool to enable training the IBM Watson Retrieve and Rank service.

Earlier today, we released a first version of the tool. Now it’s finally out there, I can share what I’ve been working on!


My video walkthrough of the IBM Watson Retrieve and Rank tool

(more…)

How to use the IBM Watson Relationship Extraction service on Bluemix

Sunday, January 25th, 2015

Before Christmas, I wrote about how I used the Watson Relationship Extraction service on Bluemix to pick out the things mentioned in news stories, as part of a mobile app we built on a hackday. I’d still like to do something more with that app, but in the meantime I should at least share how I did the Relationship Extraction bit.

From the official doc for the service:

From unstructured text, Relationship Extraction can extract entities (such as people, locations, organizations, events), and the relationships between these entities (such as person employed-by organization, person resides-in location).

This is provided as a hosted service on IBM Bluemix where any developer can sign up and give it a try.

It’s available as a documented REST API, but as part of using it in the hackday, I needed to write a bit of code around that, just to prepare the request and parse the response. I think it’ll save me time to reuse this the next time I want to build something with the API, so I’m sharing it as a standalone package.

In this post, I’ll walk though how you can use it, with a small app that grabs the contents of a BBC News story and picks out the names of people mentioned in the story.

(more…)

Watson News Companion

Friday, December 12th, 2014

newscompanion screenshotWe recently ran a hackathon at work: people within IBM were invited to try building a mobile app aimed at consumers using Watson services. It was a fun chance to try out some new ideas, as well as to build something using our APIs – dogfooding is always a good thing.

I worked on a hack with David which we submitted on Wednesday. This is what we came up with, and how we built it.

The idea

A mobile app that will help users to digest the news by explaining references in stories and providing greater context.

Background

It’s difficult to find the time nowadays to properly read and understand what’s going on in the world. We rarely have the time to sit and read through a newspaper. Instead, we might quickly read news stories online from our smartphones and tablets. But that often makes it difficult to understand the broader context that a story is in. There might be references in the story to people, places, organisations or events that are unfamiliar.

Watson could help. It could be an assistant as you read the news, explaining unfamiliar references and the broader context.

Features

Our Watson News Companion demo is a mobile news reader app that:

  • anticipates questions and suggests areas where it can help improve understanding
  • provides answers to questions without needing the users to lose their place in the story
  • allow the user to dig deeper with their own follow-up questions


A video walkthrough of the hack

(more…)

Seven years at Hursley

Monday, August 2nd, 2010

Seven years ago this week, I started at IBM. Two years ago this week, I started my current job. Thought those were worth noting.

ETS cake

I joined IBM thinking it’d be for a couple of years to get training and experience before going to do something more fun at a start-up.

But seven years (four changes of jobs, three promotions, six changes of office and nine changes of manager) later, I’m still here and still loving what I do.

What do I do at work?

Sunday, February 21st, 2010

I’ve been an Emerging Technologies Specialist for about a year and a half now. As I mentioned when I got the job, I don’t know of anywhere that I can point people at that explains what my team do.

I’ve been wary of filling this gap myself, partly because the work that the team does is so diverse that I’m not going to do us justice. But, allowing for the fact that I’ll miss a ton of cool stuff that my colleagues do, I figure that I should try and describe what I do.

I work in the Emerging Technology Services team.

How to explain this?

(more…)

Writing an offline wiki client

Saturday, October 10th, 2009

Friday was the seventh IBM Hack Day, and I again got the chance to spend a day playing with some random ideas.

As Hack Days go, I had a surprisingly productive day! I had four ideas on the day:

  • two mobile hacks (both of which I wrote a chunk of code for),
  • a twitter hack (which never got off the scribbled diagram stage, but it’s an idea I definitely want to come back to), and
  • a hack to extend an IBM product (which I created an alpha version of)

In this post, I’ll describe what I did for the last of these ideas: writing a client app for the wiki that comes with IBM’s Lotus Connections.

The idea

In the same way that I am writing this post in an offline blogging client, I wanted the same for using wikis: read and make changes to a wiki while offline, with changes uploaded to the online wiki the next time you are online.

This wasn’t a new idea. In fact, I tried it at IBM HackDay 4 back in 2007 but the wiki we used at work at the time had no API access for retrieving or updating wiki pages. So I sort of gave up and forgot about the idea.

But now I use Lotus Connections wikis at work. And Lotus Connections does have an API – an AtomPub API that gives you feeds to know when pages are changed, and a way to publish changes.

So I decided to revisit the idea.

The “finished” (ish) hack

It’s still very rough around the edges (this was a HackDay – I wrote the client code in under a day!) but it already shows the basic idea.

Offline wiki client

The top left view shows the list of your wikis.

Clicking on this fills the list below – a list of pages in the selected wiki. Clicking on a page in that list opens the contents of the page in the main view on the right.

(more…)