I am a Research Scientist at the Australian e-Health Research Centre, CSIRO (Commonwealth Scientific and Industrial Research Organisation).
My research interests are in Information Retrieval (i.e., Search). I am specifically focused on Semantic Search. I apply my research within Health Informatics — how can we improve the access, delivery and quality of health information to the people who need it.
- I completed a PhD in Information Retrieval from Queensland University of Technology in 2014.
- I hold a visiting researcher position at the School of Electrical Engineering & Computer Science, Queensland University of Technology, where I collaborate on projects with Dr Guido Zuccon and Prof. Peter Bruza.
- I've worked in research as an engineer/scientist for the University of Queensland and the Distributed Systems Technology Centre (DSTC).
- I've worked in industry as a software engineer for Mincom Limited and Permeance Technologies.
Research Interests and Current Projects
Information retrieval (the scientific field behind search engine technology) is my primary research interest. This span a number of topics/projects:
1. Semantic Search as Inference:
- My interest here is in models for semantic search: Information Retrieval (IR) models that elicit the meaning behind the words found in documents and queries rather than simply matching keywords.
- This is achieved by the integration of structured domain knowledge and data-driven information retrieval methods. A key novel components of such models is that retrieval is driven via an inference mechanism, i.e., to what extent does a information need (query) infer a document, rather than match a document.
- Finally, an important component of these models are graph-based representations and inference realised as as a traversal over the graph.
- This was the focus of my PhD thesis: "Semantic Search as Inference: Applications in Health Informatics".
2. Health Informatics and e-Health:
- Conducted with the Australian e-Health Research Centre, much of my Information Retrieval research is set within health informatics to tackle the unique challenges within this domain; specifically, how to bridge the ‘semantic gap’; that is, how to overcome the mismatch between raw medical data and the way human beings interpret it.
- This may be a problem for medical professionals searching patients records, for researchers trying to search for eligible patients for clinical trials or even for the public trying to search for accurate, reliable and readable health information online. Overcoming some of these challenges in health informatics has the potential to have significant impact into an issue that is critical to us all: our health.
- B. Koopman, G. Zuccon, and P. Bruza. What makes an effective clinical query and querier? Journal of the Association for Information Science and Technology, 68(11):2557-2571, 2017.Journal
- B. Koopman, L. Cripwell, and G. Zuccon. Generating clinical queries from patient narratives: A comparison between machines and humans. In SIGIR, Tokyo, Japan, August 2017.Short paper
- B. Koopman, G. Zuccon, and J. Russell. A task-oriented search engine for evidence-based medicine. In SIGIR demo, Tokyo, Japan, August 2017.Demo paper
- H. Scells, G. Zuccon, B. Koopman, A. Deacon, and S. Geva. A test collection for evaluating retrieval of studies for inclusion in systematic reviews. In SIGIR, Tokyo, Japan, August 2017.Short paper
- G. Zuccon and B. Koopman. SIGIR 2017 tutorial on health search (HS2017): A full-day from consumers to clinicians. SIGIR Tutorial, Tokyo, Japan, August 2017. Tutorial
- B. Koopman, J. Russell, and G. Zuccon. Task-oriented search for evidence-based medicine. International Journal of Digital Libraries, 2017.Journal
- Jimmy, G. Zuccon, and B. Koopman. Boosting titles does not generally improve retrieval effectiveness. In Proceedings of the 21st Australasian Document Computing Symposium, ADCS ’16, pages 25–32, Melbourne, Australia, 2016. Long paper
- H. Hassanzadeh, A. Nguyen, and B. Koopman. Evaluation of medical concept annotation systems on clinical records. In Proceedings of the Australasian Language Technology Association Workshop 2016, pages 15–24, Melbourne, Australia, December 2016.Long paper
- A. Lipani, G. Zuccon, M. Lupu, B. Koopman, and A. Hanbury. The impact of fixed-cost pooling strategies on test collection bias. In International Conference on the Theory of Information Retrieval (ICTIR), Newark, USA, September 2016.Short paper
- B. Koopman and G. Zuccon. A test collection for matching patients to clinical trials. In Proceedings of the 39th annual international ACM SIGIR conference on research and development in information retrieval, Pisa, July 2016. Short paper
- G. Zuccon, B. Koopman, P. Bruza, and L. Azzopardi. Integrating and evaluating neural word embeddings in information retrieval. In Australasian Document Computing Symposium (ADCS), Sydney, Australia, December 2015. Long paper
- B. Koopman, G. Zuccon, P. Bruza, L. Sitbon, and M. Lawley. Information retrieval as semantic inference: A graph inference model applied to medical search. Information Retrieval, 19(1):6–37, 2015.Journal
- B. Koopman, G. Zuccon, A. Nguyen, A. Bergheim, and N. Grayson. Automatic ICD-10 classification of cancers from free-text death certificates. Journal of Medical Informatics, 84(11):956–965, 2015. Journal
- B. Koopman, G. Zuccon, A. Wagholikar, K. Chu, J. O’Dwyer, A. Nguyen, and G. Keijzers. Automated reconciliation of radiology reports and discharge summaries. In American Medical Informatics Association Annual Symposium (AMIA), November 2015. Long paper
- B. Koopman, S. Karimi, A. Nguyen, R. McGuire, D. Muscatello, M. Kemp, D. Truran, M. Zhang, and S. Thackway. Automatic classification of diseases from free-text death certificates for real-time surveillance. BMC Medicial Informatics and Decision Making, 15(1):1–10, 2015.Journal
- G. Zuccon, B. Koopman, and J. Palotti. Diagnose this if you can: On the effectiveness of search engines in finding medical self-diagnosis information. In European Conference on Information Retrieval (ECIR), April 2015. Short paper Data
- Bevan Koopman. Semantic search as inference: Applications in health informatics. SIGIR Forum, 48(2):116–117, December 2014. Journal
- B. Koopman and G. Zuccon. Document timespan normalisation and understanding temporality for clinical records search. In Proceedings of the 19th Australasian Document Computing Symposium, Melbourne, Australia, November 2014. Short paper
- S. Mirhosseini, G. Zuccon, B. Koopman, A. Nguyen, and M. Lawley. Medical free-text to concept mapping as an information retrieval problem: An initial investigation. In Proceedings of the 19th Australasian Document Computing Symposium, Melbourne, Australia, November 2014. Short paper
- G. Zuccon, B. Koopman, and P. Bruza. Exploiting inference from semantic annotations for information retrieval: Reflections from medical IR. In Seventh International Workshop on Exploiting Semantic Annotations in Information Retrieval, Shanghai, China, November 2014. Workshop paper
- L. Sitbon, M. Kholghi, G. Zuccon, A. Nguyen, B. Koopman, and M. Lawley. Delivering clinical information extraction tools to practitioners. In Macquarie University Workshop on Natural Language of Clinical Text (MQClinicalNLP), Sydney, Australia, September 2014. Workshop paper
- G. Zuccon, B. Koopman, and P. Bruza. Towards exploiting inference from semantic annotations for medical information retrieval. In Macquarie University Workshop on Natural Language of Clinical Text (MQClinicalNLP), Sydney, Australia, September 2014. Workshop paper
- L. D. Vine, G. Zuccon, B. Koopman, L. Sitbon, and P. Bruza. Medical semantic similarity with a neural language model. In 23rd ACM International Conference on Information and Knowledge Management (CIKM), Shanghai, China, November 2014. Short paper
- B. Koopman and G. Zuccon. Why assessing relevance in medical IR is demanding. In Proceedings of the SIGIR Workshop on Medical Information Retrieval (MedIR), Gold Coast, Australia, July 2014. Workshop paper Data
- G. Zuccon and B. Koopman. Integrating understandability in the evaluation of consumer health search engines. In Proceedings of the SIGIR Workshop on Medical Information Retrieval (MedIR), Gold Coast, Australia, July 2014. Workshop paper
- B. Koopman and G. Zuccon. Relevation!: An open source system for information retrieval relevance assessment. In Proceedings of the 37th annual international ACM SIGIR conference on research and development in information retrieval, Gold Coast, Australia, July 2014. [abstract] Demo paper Code
- B. Koopman and G. Zuccon. Understanding negation and family history to improve clinical information retrieval. In Proceedings of the 37th annual international ACM SIGIR conference on research and development in information retrieval, Gold Coast, Australia, July 2014. [abstract] Short paper
- Bevan Koopman. Semantic search as inference: Applications in health informatics. PhD Thesis, Queensland University of Technology, May 2014. PhD Thesis
Relevation! is a system for performing relevance judgements for information retrieval evaluation. Relevation! is web-based, fully configurable and expandable; it allows researchers to effectively collect assessments and additional qualitative data. The system is easily deployed allowing assessors to smoothly perform their relevance judging tasks, even remotely. Relevation! is available as an open source project http://ielab.github.io/relevation.
We present a study to understand the effect that negated terms (e.g., ``no fever") and family history (e.g., ``family history of diabetes") have on searching clinical records. Our analysis is aimed at devising the most effective means of handling negation and family history. In doing so, we explicitly represent a clinical record according to its different content types: negated, family history and normal content; the retrieval model weights each of these separately. Empirical evaluation shows that overall the presence of negation harms retrieval effectiveness while family history has little effect. We show negation is best handled by weighting negated content (rather than the common practise of removing or replacing it). However, we also show that many queries benefit from the inclusion of negated content and that negation is optimally handled on a per-query basis. Additional evaluation shows that adaptive handing of negated and family history content can have significant benefits.
- B. Koopman, G. Zuccon, L. De Vine, A. Bakharia, P. Bruza, L. Sitbon, and A. Gibson. ADCS reaches adulthood: an analysis of the conference and its community over the last eighteen years. In Proceedings of the 18th Australasian Document Computing Symposium, pages 34–41, Brisbane, Australia, December 2013. Long paper Data
- G. Zuccon, B. Koopman, and A. Nguyen. Retrieval of health advice on the web: AEHRC at Share/CLEF 2013 eHealth Evaluation Lab Task 3. In Proceedings of CLEF Workshop on Cross-Language Evaluation of Methods, Applications, and Resources for eHealth Document Analysis, Valencia, Spain, September 2013. Long paper
- G. Zuccon, A. Holloway, B. Koopman, and A. Nguyen. Identify disorders in health records using conditional random fields and metamap: AEHRC at Share/CLEF 2013 eHealth Evaluation Lab Task 1. In Proceedings of CLEF Workshop on Cross-Language Evaluation of Methods, Applications, and Resources for eHealth Document Analysis, Valencia, Spain, September 2013. Long paper
- M. Symonds, P. Bruza, G. Zuccon, B. Koopman, L. Sitbon, and I. Turner. Automatic query expansion: a structural linguistic perspective. Journal of the American Society for Information Science and Technology (JASIST), In Press, 2013. Journal paper
- Wittek, P., Koopman, B., Zuccon, G. and Daranyi, S., 2013. Combining Word Semantics within Complex Hilbert Space for Information Retrieval. In Quantum Interaction. Leicester, UK. Long paper
- Anthony Nguyen, Derek Ireland, Guido Zuccon, Deanne Vickers, Bevan Koopman, Michael Lawley, 2013. Streaming medical report analytics at increasingly "Big Data" scale. In Big Data in Health. Melbourne, Australia. Long paper
- Symonds, M., Zuccon, G., Koopman, B. and Bruza, P., 2012. QUT Para at TREC 2012 Web Track : Word Associations for Retrieving Web Documents. In Proceedings of 21st Text REtrieval Conference (TREC 2012). Long paper
- Bevan Koopman, Zuccon, G., Nguyen, A., Vickers, D., Butt, L. and Bruza, P., 2012. Exploiting SNOMED CT Concepts & Relationships for Clinical Information Retrieval: Australian e-Health Research Centre and Queensland University of Technology at the TREC 2012 Medical Track. In Proceedings of 21st Text REtrieval Conference (TREC 2012). Long paper
- Zuccon, G., Koopman, B., Nguyen, A., Vickers, D. and Butt, L., 2012. Exploiting Medical Hierarchies for Concept-based Information Retrieval. In Proceedings of the Seventeenth Australasian Document Computing Symposium. Short paper
- Koopman, B., Bruza, P., Zuccon, G., Lawley, M. and Sitbon, L., 2012. Graph-based Concept Weighting for Medical Information Retrieval [Slides]. In Proceedings of the Seventeenth Australasian Document Computing Symposium. [abstract] Long paper
- Symonds, M., Zuccon, G., Koopman, B., Bruza, P. and Nguyen, A.N., 2012. Semantic Judgement of Medical Concepts: Combining Syntagmatic and Paradigmatic Information. In Australasian Language Technology Workshop. Long paper
- Koopman, B., Zuccon, G., Bruza, P., Sitbon, L., & Lawley, M. An Evaluation of Corpus-driven Measures of Medical Concept Similarity for Information Retrieval. 21st ACM International Conference on Information and Knowledge Management (CIKM). Maui, USA, October 2012. Short paper
- Koopman, B., Bruza, P., Sitbon, L., Lawley, M. (2012). Towards Semantic Search and Inference in Electronic Medical Records: an approach using Concept-based Information Retrieval. Australasian Medical Journal: Special Issue on Artificial Intelligence in Health, 5(9), pp.482–488. Journal
This paper presents a graph-based method to weight med- ical concepts in documents for the purposes of information retrieval. Medical concepts are extracted from free-text doc- uments using a state-of-the-art technique that maps n-grams to concepts from the SNOMED CT medical ontology. In our graph-based concept representation, concepts are vertices in a graph built from a document, edges represent associations between concepts. This representation naturally captures dependencies between concepts, an important requirement for interpreting medical text, and a feature lacking in bag- of-words representations. We apply existing graph-based term weighting methods to weight medical concepts. Using concepts rather than terms addresses vocabulary mismatch as well as encapsu- lates terms belonging to a single medical entity into a sin- gle concept. In addition, we further extend previous graph- based approaches by injecting domain knowledge that esti- mates the importance of a concept within the global medical domain. Retrieval experiments on the TREC Medical Records col- lection show our method outperforms both term and concept baselines. More generally, this work provides a means of integrating background knowledge contained in medical ontologies into data-driven information retrieval approaches.
- B. Koopman, P. Bruza, L. Sitbon, and M. Lawley, AEHRC & QUT at TREC 2011 Medical Track : a concept-based information retrieval approach. Proceedings of 20th Text REtrieval Conference (TREC 2011), Gaithersburg, MD, USA, November 2011. Long paper
- Koopman, B., Bruza, P., Sitbon, L., Lawley, M. Towards semantic search and inference in electronic medical records: an approach using concept-based information retrieval. Proceedings of the 1st Australian Workshop on Artificial Intelligence in Health (AIH 2011), Perth, December 2011. Long paper
- Koopman, B., Bruza, P., Sitbon, L., Lawley, M. Evaluating medical information retrieval. Proceedings of the 34st annual international ACM SIGIR conference on research and development in information retrieval, Beijing, August 2011. Short paper
- Koopman, B., Bruza, P., Sitbon, L., Lawley, M. Analysis of the effect of negation on information retrieval of medical data. Proceedings of the Fifteenth Australasian Document Computing Symposium (ADCS), Melbourne, December 2010. Short paper
- Koopman, B., Bruza, P., Lawley, M., Sitbon, L. Semantic search and inferencing in health informatics. Proceedings of the 2010 CSIRO ICT Conference, Sydney, November 2010. Short paper
- Hunter J., Schroeter R., Koopman B., Henderson M. Using the Semantic Grid to Build Bridges between Museums and Indigenous Communities. Global Grid Forum: Semantic Grid Application Workshop, Hawaii. June 2004.Long paper
- Hunter J., Koopman B., Sledge J. Software Tools for Indigenous Knowledge Management. Museums and the Web 2003, September 2003. Long paper
- Koopman, B. Software Tools for Indigenous Knowledge Management. Honours Thesis. School of Information Technology and Electrical Engineering, University of Queensland, Brisbane. 2002. Honours Thesis