Archive for the ‘Auto Tagging’ Category

Web Page Structure, Without The Semantic Web

Saturday, May 30th, 2015

Could a Little Startup Called Diffbot Be the Next Google?

From the post:


Diffbot founder and CEO Mike Tung started the company in 2009 to fix a problem: there was no easy, automated way for computers to understand the structure of a Web page. A human looking at a product page on an e-commerce site, or at the front page of a newspaper site, knows right away which part is the headline or the product name, which part is the body text, which parts are comments or reviews, and so forth.

But a Web-crawler program looking at the same page doesn’t know any of those things, since these elements aren’t described as such in the actual HTML code. Making human-readable Web pages more accessible to software would require, as a first step, a consistent labeling system. But the only such system to be seriously proposed, Tim Berners-Lee’s Semantic Web, has long floundered for lack of manpower and industry cooperation. It would take a lot of people to do all the needed markup, and developers around the world would have to adhere to the Resource Description Framework prescribed by the World Wide Web Consortium.

Tung’s big conceptual leap was to dispense with all that and attack the labeling problem using computer vision and machine learning algorithms—techniques originally developed to help computers make sense of edges, shapes, colors, and spatial relationships in the real world. Diffbot runs virtual browsers in the cloud that can go to a given URL; suck in the page’s HTML, scripts, and style sheets; and render it just as it would be shown on a desktop monitor or a smartphone screen. Then edge-detection algorithms and computer-vision routines go to work, outlining and measuring each element on the page.

Using machine-learning techniques, this geometric data can then be compared to frameworks or “ontologies”—patterns distilled from training data, usually by humans who have spent time drawing rectangles on Web pages, painstakingly teaching the software what a headline looks like, what an image looks like, what a price looks like, and so on. The end result is a marked-up summary of a page’s important parts, built without recourse to any Semantic Web standards.

The irony here, of course, is that much of the information destined for publication on the Web starts out quite structured. The WordPress content-management system behind Xconomy’s site, for example, is built around a database that knows exactly which parts of this article should be presented as the headline, which parts should look like body text, and (crucially, to me) which part is my byline. But these elements get slotted into a layout designed for human readability—not for parsing by machines. Given that every content management system is different and that every site has its own distinctive tags and styles, it’s hard for software to reconstruct content types consistently based on the HTML alone.

There are several themes here that are relevant to topic maps.

First, it is true that most data starts with some structure, styles if you will, before it is presented for user consumption. Imagine an authoring application that automatically and unknown to its user, metadata that can then provide semantics for its data.

Second, the recognition of structure approach being used by Diffbot is promising in the large but should also be promising in the small as well. Local documents of a particular type are unlikely to have the variance of documents across the web. Meaning that with far less effort, you can build recognition systems that can empower more powerful searching of local document repositories.

Third, and perhaps most importantly, while the results may not be 100% accurate, the question for any such project should be how much accuracy is required? If I am mining social commentary blogs, a 5% error rate on recognition of speakers might be acceptable, because for popular threads or speakers, those errors are going to be quickly corrected. Unpopular threads or authors never followed, does that come under no harm/no foul?

Highly recommended for reading/emulation.

Shining a light into the BBC Radio archives

Monday, December 15th, 2014

Shining a light into the BBC Radio archives by Yves Raimond, Matt Hynes, and Rob Cooper.

From the post:

comma

One of the biggest challenges for the BBC Archive is how to open up our enormous collection of radio programmes. As we’ve been broadcasting since 1922 we’ve got an archive of almost 100 years of audio recordings, representing a unique cultural and historical resource.

But the big problem is how to make it searchable. Many of the programmes have little or no meta-data, and the whole collection is far too large to process through human efforts alone.

Help is at hand. Over the last five years or so, technologies such as automated speech recognition, speaker identification and automated tagging have reached a level of accuracy where we can start to get impressive results for the right type of audio. By automatically analysing sound files and making informed decisions about the content and speakers, these tools can effectively help to fill in the missing gaps in our archive’s meta-data.

The Kiwi set of speech processing algorithms

COMMA is built on a set of speech processing algorithms called Kiwi. Back in 2011, BBC R&D were given access to a very large speech radio archive, the BBC World Service archive, which at the time had very little meta-data. In order to build our prototype around this archive we developed a number of speech processing algorithms, reusing open-source building blocks where possible. We then built the following workflow out of these algorithms:

  • Speaker segmentation, identification and gender detection (using LIUM diarization toolkitdiarize-jruby and ruby-lsh). This process is also known as diarisation. Essentially an audio file is automatically divided into segments according to the identity of the speaker. The algorithm can show us who is speaking and at what point in the sound clip.
  • Speech-to-text for the detected speech segments (using CMU Sphinx). At this point the spoken audio is translated as accurately as possible into readable text. This algorithm uses models built from a wide range of BBC data.
  • Automated tagging with DBpedia identifiers. DBpedia is a large database holding structured data extracted from Wikipedia. The automatic tagging process creates the searchable meta-data that ultimately allows us to access the archives much more easily. This process uses a tool we developed called ‘Mango’.

,,,

COMMA is due to launch some time in April 2015. If you’d like to be kept informed of our progress you can sign up for occasional email updates here. We’re also looking for early adopters to test the platform, so please contact us if you’re a cultural institution, media company or business that has large audio data-set you want to make searchable.

This article was written by Yves Raimond (lead engineer, BBC R&D), Matt Hynes (senior software engineer, BBC R&D) and Rob Cooper (development producer, BBC R&D)

I don’t have a large audio data-set but I am certainly going to be following this project. The results should be useful in and of themselves, to say nothing of being a good starting point for further tagging. I wonder if the BBC Sanskrit broadcasts are going to be available? I will have to check on that.

Without diminishing the achievements of other institutions, the efforts of the BBC, the British Library, and the British Museum are truly remarkable.

I first saw this in a tweet by Mike Jones.

Auto Tagging Articles using Semantic Analysis and Machine Learning

Wednesday, May 2nd, 2012

Auto Tagging Articles using Semantic Analysis and Machine Learning

Description:

The idea is to implement an auto tagging feature that provides tags automatically to the user depending upon the content of the post. The tags will get populated as soon as the user leaves the focus on the content text area or via ajax on the press of a button.I’ll be using semantic analysis and topic modeling techniques to judge the topic of the article and extract keywords also from it. Based on an algorithm and a ranking mechanism the user will be provided with a list of tags from which he can select those that best describe the article and also train a user-content specific semi-supervised machine learning model in the background.

A Drupal sandbox for work on auto tagging posts.

Or, topic map authoring without being “in your face.”

Depends on how you read “tags.”