Feeds:
Posts
Comments

Archive for the ‘Text analytics’ Category

I am currently hiring for the following position. If you know of anyone suitable, please encourage them to apply!

Research Associate in the field of information retrieval / user experience (0.5 FTE)

This role is part of a Google-funded research project that aims to use AI (Artificial Intelligence) and data visualization to facilitate more efficient and effective approaches to information retrieval through the development of alternative approaches to search strategy formulation. This has the potential to minimize error and inefficiency in scientific research and facilitate more efficient and effective research workflows for the broader scientific community.

(more…)

Read Full Post »

I am recruiting sponsored or self-funded PhD students who wish to undertake projects in natural language processing and UX with focus on information retrieval, including the projects listed below.

Note that these topics are based on MSc level project proposals, but most have the scope and ambition to be scalable to PhD level work. Moreover, they are merely ideas at this stage, so feel free to adapt / enhance them to accommodate your own ideas and interests. Note also that this list is not exhaustive: we have other project ideas and proposals which aren’t quite ready for public dissemination.

If you are a self-funded student considering a PhD in any of the topics below please take a look at the further information and/or email me to discuss.

(more…)

Read Full Post »

Delighted to announce a new release of 2Dsearch, with various improvements including new preferences with options for snap-to-grid, advanced query parsing and default databases. We’ve also integrated the latest version of PolyGlot and fixed the query parser bug which so many of you raised.

What this means is that you can now use 2Dsearch to execute a single visual search across a dozen different databases and benefit from automated translations for many more. We’ve also made further improvements to the user experience and now provide example searches for each of the databases.

We’ve lots more planned for the next release, so if you’d like to help shape this or have comments or suggestions then please let us know.

Read Full Post »

In this short video we take a brief look at searching grey literature. Grey literature is the term given to unpublished documents such as dissertations, technical reports, conference abstracts, newsletters, presentations and so on. Even though they may not have been formally published, these documents can still contain vital information.

(more…)

Read Full Post »

In this short video we learn how to automatically translate search strategies to the syntax of different databases.

Let’s start with a simple search strategy that finds documents on the use of exercise to prevent obesity in older people:

(more…)

Read Full Post »

Spring is traditionally a time of new beginnings, so I am delighted this week to announce a new release of 2Dsearch. This release contains a variety of bug fixes and improvements, including support for two new databases: ACM Guide to Computing Literature and IDEAS (the largest bibliographic database dedicated to Economics available freely on the Internet). We’ve also improved our search report generation tool and now offer query statistics to help you refine those all important search strategies.

What all this means is that you can now use 2Dsearch to search visually across 12 different databases and use automated translations for 8 more. We’ve also made further improvements to the user experience and now provide example searches for each of the 12 databases.

We’ve lots more planned for the next release, so if you’d like to help shape this and/or have comments or suggestions then do let us know. We’d be delighted to hear from you!

Read Full Post »

I am currently starting work on developing an undergraduate module in Natural Language Processing (level 6, 3rd year). Although I have been involved in the field of NLP for many years, recent times have witnessed a transformation of the field, not just in terms of its academic foundations, but also its practical application in industry and its attractiveness as a fulfilling and rewarding career choice. My sense is that some of the topics which I originally studied for my doctorate retain their appeal since the key ideas remain relevant despite radical changes in the implementation. However, others are more hostage to the technological fortunes of deep learning and other neural/distributional approaches.

My view is that field benefits by being informed by more than one perspective: computer/data science may be a given, but cognitive science, information science and linguistics all have their contributions to make. Clearly, it is a tricky task to pack all this into just 10 topics, and to do so from both a theoretical and practical perspective. Here is my current thinking:

(more…)

Read Full Post »

New year, new release — I am delighted this week to announce a new release of 2Dsearch. This contains a variety of bug fixes and improvements, including support for IEEE XPlore, a ‘Help me choose’ feature and automated search report generation.

You can now use 2Dsearch to search visually across 10 different databases and use automated translations for many more. We’ve also made improvements to the canvas user experience and now provide starter examples for each of the 10 databases.

We’ve lots more planned for the next release, so if you’d like to help shape this and/or have comments or suggestions then do let us know. We’d be delighted to hear from you.

Read Full Post »

Image credit: https://bigarrowgroup.com/tortoise-hare-marketing/

Great to see so many old (and new) faces at Search Solutions 2020 last month. A new format for us, being wholly virtual, but I think the change did us good, and in some ways reinvigorated the event. Looking forward to next years event already… In the meantime, here are the slides from my talk ‘Searching Fast and Slow‘. This talk makes the case for a transformation of professional search from a paradigm based on monolithic, static, procedural strings to one based on interactive, declarative, executable objects, with corresponding benefits in transparency, reproducibility and effectiveness. As always, comments and feedback welcome.

(more…)

Read Full Post »

Last week I was honored and privileged to give a talk at EAHIL 2020 (European Association for Health Information and Libraries) on the topic of An open-access platform to design, validate and share search strategies. This is joint work with Farhad Shokraneh of King’s College. Delighted to say our talk generated a number of interesting discussions and follow ups. Our slides are attached below: comments and feedback welcome.

(more…)

Read Full Post »

Older Posts »