A draft syllabus for Natural Language Processing

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:

Read Full Post »

2Dsearch: new year, new release

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 »

Searching fast and slow

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.

Read Full Post »

An open-access platform to design, validate and share search strategies

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.

Read Full Post »

Visual approaches to patent retrieval

Last week I was privileged to present to the British Patent Information Professionals group (BPIP) on the subject of visual approaches to patent retrieval. Many thanks to Jeanette Eldridge for making this happen, and a pleasure to renew the acquaintance with Stephen Adams, Jane List and Nathan Pennington. My slides are attached below, comments and feedback welcome. Next step: integration with Google Patents, perhaps?

Read Full Post »

2Dsearch: latest release including ERIC

It’s been a little while in the making, but I am delighted this week to announce a new release of 2Dsearch. This contains a variety of bug fixes and improvements, notably support for ERIC (Education Resources Information Center).

You can now use 2Dsearch to search visually across 9 different databases and use automated translations for many more. We’ve made various improvements to the canvas user experience, including support for proximity operators and creating nested groups. We also improved the query parsing and now provide in-app links to syntax guides and other support materials.

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

Read Full Post »

Using controlled vocabulary terms to optimize your search

In the previous video we learnt how to use search suggestions to help us choose effective keywords for our search. In this video, we’ll look at techniques to make those terms more precise.

A key task in developing effective search strategies is choosing the right terms for the various facets of your information need. For example, if you are researching the topic of promoting physical activity to prevent obesity in older people, you might start with a search like this:

Read Full Post »

Towards explainability in professional search

On Friday I was privileged to present a paper called ‘Towards Explainability in Professional Search‘ at the 3rd International Workshop on ExplainAble Recommendation and Search (EARS 2020), part of SIGIR 2020. This paper was co-presented with my colleague Andy MacFarlane of City University, and represents our collective thoughts and recommendations on how to develop more transparent, reproducible and explainable systems in professional search. Understandably, given our respective geographic locations the presentation was made remotely, and we are thankful for the local attendees who stayed around until 22:00 (local time) for our talk. The slides are available below. We view these recommendations as a conversation starter rather than the last word, so comments & feedback are particularly welcome. The paper itself is available for download from the EARS website.

Read Full Post »

How to optimize your search using query suggestions

In our previous video we learnt how to use visual approaches to create the correct structure for our search strategy. In this video, we’ll look at techniques to create the right content.

A key task in developing effective search strategies is choosing the right keywords. But how do we create these terms in the first place? One way is simply to brainstorm them, i.e. think up related terms for each facet. Or you might use your search results as a source of inspiration. But is there a more efficient way to generate related terms?

Read Full Post »

Putting search theory to work on large datasets

Last week I was privileged to present at the Singapore Chapter of ISKO on the topic of “Putting search theory to work on large datasets“. Understandably, given our respective geographic locations this presentation was made remotely, but I’m pleased to say we had a good attendance and a very informative discussion. Big thanks go to Patrick Lambe, Maish Nichani and Mark Garlinghouse for making this happen. The slides are available below, and the video should follow shortly. As always, comments & feedback welcome 🙂

Read Full Post »