Search Solutions is the premier UK forum for the presentation of the latest innovations in search and information retrieval.
The 2021 conference was again a virtual event because of the constraints on the number of delegates that the BCS London office is able to accommodate to reflect COVID guidelines. There was a programme of tutorials on Tuesday 23 November and the took place on Wednesday 24 November.
The Conference Committee members were Charlie Hull, Ingo Frommholz, Haiming Liu, Tony Russell-Rose and Martin White.
The Tutorials 23 November 2021
Tutorial 1 Overview of Natural Language Processing
BCS, Ground Floor, 25 Copthall Avenue, London, EC2R 7BP
This tutorial will give an overview of Natural Language Processing, which is the computer processing of human-produced speech and text). The textbook “Speech and Language Processing” by Daniel Jurafsky and James H Martin will be used as a basis for the tutorial. The levels we will cover are morphology (shapes of subword units), phonology (pronunciation of subword units), spelling checkers, automatic assignment of grammatical classes to words, relations among words, parsing with context-free grammars, meaning representations, word sense disambiguation, pragmatics (language above the sentence level) and a brief introduction to machine translation.
Information systems that are deployed in production settings and used operationally by hundreds or thousands of users are typically more complex than systems developed in academic research, which makes them much harder to evaluate. However, not evaluating a system is not a viable option, as it corresponds to “flying blindly” - the positive or negative impact of any change would remain unknown. As a consequence, many practitioners come up with their own protocols for assessing system quality in terms of the relevance of rankings given a query. In the academic world, several initiatives such as TREC1, MediaEval2 or CLEF3 are striving to provide benchmarks and datasets to make different solutions and algorithms comparable to each other for some specified task.
A further example is Kaggle4. While BCS Search Solutions in the past has been successful in transferring knowledge among practitioners on the one hand, and academics and practitioners, on the other hand, we think evaluation is a topic that would require more attention. While we think there is no “one size fits all” solution, we also believe that there should be an exchange of ideas, solutions and experiences when it comes to evaluation information and search systems in an enterprise environment.
Search Solutions 24 November 2021
Session themes and speakers
Chair: Professor Udo Kruschwitz
Professor Katriina Byström, Department of Archivistics, Library and Information Science, Oslo Metropolitan University
Formulating and treating information needs at work
In this talk, information needs are placed into a workplace context. These information needs often activate a tracing strategy in searching for information from multiple information sources.
10.00 Training for IR and data science
- Professor Paul Clough, Information School, University of Sheffield and Peak Indicators
- Olivia Foulds, Department of Computer Science, University of Strathclyde
Crossing the 49th Parallel in Data and Information Science
In this joint session we consider the 49th parallel within the data and information fields, especially the divide between academia and industry, disciplines and perspectives. Paul Clough will reflect on the divide between business and academia, providing examples of what boundaries may exist and ways of crossing borders. In short we will consider whether businesses and universities are in sync?
Olivia Foulds will discuss her work in considering psychology during Information Retrieval. Through a few different studies involving visual clutter during learning, individual differences in perceptual speed, online advertisements, and healthcare during COVID, Olivia will emphasize the importance of putting the user first when designing effective interfaces.
11.00 Identifying and addressing misinformation
Dr. Andy MacFarlane, City, University of London
Supporting verification and exploration of Information in Journalism: the DMINR approach.
The verification and exploration of information are a critical working practice in the field of journalism. We present DMINR, a system that extracts relationships between entities using named entity recognition (NER) to support these activities.
Dr. David Corney, Senior Data Scientist, Full Fact
Claim matching: find repeats of misleading claims
After fact checkers have researched a misleading claim and published a fact check article, we search for any repeats of that claim in the media using a combination of IR, NLP and ML techniques.
12.00 Searching the enterprise
Steve Sale, Senior Search Architect, AstraZeneca
Searching the Enterprise
This presentation will discuss how AstraZeneca has handled the challenges of searching a Global Enterprise with a broad range of business areas from Research, Manufacturing and Marketing to back office functions such as HR, IT & Legal.
Three tipping points in enterprise search
The impact and challenges of adopting AI solutions, the management of enterprise search procurement projects and the importance of building solutions around well-defined requirements for user interfaces will be considered. Martin White, Intranet Focus Ltd.
Chair Martin White, Visiting Professor, Information School, University of Sheffield
14.00 Systematic searching
Drs. Ing Rene Spijker, Academic Medical Centre, University of Amsterdam
Looking back - looking forward
The role of systematic search during the Covid pandemic is reviewed, identifying lessons learned that could be of benefit in future pandemic events
15.00 Digital asset management
Tim Gollins, Head of Preservation and Information Management, National Records of Scotland
Fairly Finding the Past - The Challenges of Information Retrieval in Public Sector Archives.
Some examples of the challenges faced by archival institutions in making their collections fairly searchable using the collection of the National Records of Scotland as an example.”
Theresa Regli, DAM industry analyst and strategy consultant
Searching for brand, video, and photography assets in the enterprise
This session will show examples of commercial DAM solutions and their search features, in particular demonstrating the cross-section of DAM and PIM (Product Information Management) solutions for marketing and advertising.
16.00 Panel Session - What might be the The themes of Search Solutions 2022
- Professor Katriina Bystrom, University of Oslo
- Professor Iadh Ounis University of Glasgow
- Scott Parker, Director of Product Marketing, Sinequa
- Charlie Hull, Open Source Connections
17.00 BCS IRSG AGM