Bevan R. Koopman

Researcher in Search & Language Technologies

About Me

I'm a researcher focused on search and language technologies. I lead the Health Search team at the Australian e-Health Research Centre, CSIRO (Commonwealth Scientific and Industrial Research Organisation) and I'm an Associate Professor in Language Technologies at the School of Information Technology and Electrical Engineering, Univeristy of Queensland.

At its core, my research has been about helping people find relevant and reliable health information to make health related decisions.

From a clinical perspective then, my research is to tackle problems where people need to find answers and make clinical decisions in the face of overwhelming amounts of typically unstructured data. So that might be in evidence-based medicine, where clinicians need to search through vast amounts of literature and clinical trials to find a targeted treatment for a specific cancer. It can be automating the processing of matching and recruiting a patient to a clinical trials.

From a technical perspective, the key challenges here are 1) how to build models search through unstructured natural language; 2) understanding the semantics of someones query rather than just matching keywords; 3) how to inject medical domain knowledge into an AI model; 4) putting the human searcher in the loop so they can bring their domain knowledge to guide the model to relevant information; 5) the underlying techniques nowadays being training specific deep learning based ranking models.

Contact

Australian e-Health Research Centre
Lvl 7, STARS Hospital, 296 Herston Rd, Herston, Queensland 4029, AUSTRALIA.
(Location on Google Maps)
Email: bevan.koopman@csiro.au

Publications

2024

  • B. Koopman and G. Zuccon. Dr chatgpt, tell me what i want to hear: How prompt knowledge impacts health answer correctness. In EMNLP, December 2023..Long paper
  • J. Liu, A. Nicolson, J. Dowling, B. Koopman, and A. Nguyen. e-health csiro at” discharge me!” 2024: Generating discharge summary sections with fine-tuned language models. arXiv preprint arXiv:2407.02723, 2024.Long paper
  • X. Mao, B. Koopman, and G. Zuccon. A reproducibility study of goldilocks: Just-right tuning of bert for tar. In European Conference on Information Retrieval, pages 132–146. Springer, Cham, 2024.Long paper
  • X. Mao, S. Zhuang, B. Koopman, and G. Zuccon. Dense retrieval with continuous explicit feedback for systematic review screening prioritisation. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 2357–2362, 2024.Short paper
  • A. Nicolson, J. Liu, J. Dowling, A. Nguyen, and B. Koopman. e-health csiro at rrg24: Entropy-augmented self-critical sequence training for radiology report generation. arXiv preprint arXiv:2408.03500, 2024.Long paper
  • A. Nicolson, S. Zhuang, J. Dowling, and B. Koopman. The impact of auxiliary patient data on automated chest x-ray report generation and how to incorporate it. arXiv preprint arXiv:2406.13181, 2024.Long paper
  • F. Schlatt, M. Fr ̈obe, H. Scells, S. Zhuang, B. Koopman, G. Zuccon, B. Stein, M. Potthast, and M. Hagen. Set-encoder: Permutation-invariant inter-passage attention for listwise passage re-ranking with cross-encoders. arXiv preprint arXiv:2404.06912, 2024.Long paper
  • F. Schlatt, M. Fr ̈obe, H. Scells, S. Zhuang, B. Koopman, G. Zuccon, B. Stein, M. Potthast, and M. Hagen. A systematic investigation of distilling large language models into cross-encoders for passage re-ranking. arXiv preprint arXiv:2405.07920, 2024.Long paper
  • S. Wang, H. Scells, S. Zhuang, M. Potthast, B. Koopman, and G. Zuccon. Zero-shot generative large language models for systematic review screening automation. In European Conference on Information Retrieval, pages 403–420. Springer, Cham, 2024.Long paper
  • S. Wang, S. Zhuang, B. Koopman, and G. Zuccon. Resllm: Large language models are strong resource selectors for federated search. arXiv preprint arXiv:2401.17645, 2024.Long paper
  • C. Yu, H. Li, A. Mourad, B. Koopman, and G. Zuccon. TPRF: A transformer-based pseudo-relevance feedback model for efficient and effective retrieval. arXiv preprint arXiv:2401.13509, 2024.Long paper
  • S. Zhuang, B. Koopman, X. Chu, and G. Zuccon. Understanding and mitigating the threat of vec2text to dense retrieval systems. arXiv preprint arXiv:2402.12784, 2024.Long paper
  • S. Zhuang, B. Koopman, and G. Zuccon. Team ielab at trec clinical trial track 2023: Enhancing clinical trial retrieval with neural rankers and large language models. arXiv preprint arXiv:2401.01566, 2024.Notebook
  • S. Zhuang, B. Liu, B. Koopman, and G. Zuccon. Open-source large language models are strong zero-shot query likelihood models for document ranking. In EMNLP Findings, December 2023.Long paper
  • S. Zhuang, X. Ma, B. Koopman, J. Lin, and G. Zuccon. Promptreps: Prompting large language models to generate dense and sparse representations for zero-shot document retrieval. arXiv preprint arXiv:2404.18424, 2024.Long paper
  • S. Zhuang, H. Zhuang, B. Koopman, and G. Zuccon. A setwise approach for effective and highly efficient zero-shot ranking with large language models. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 38–47, 2024.Long paper

2023

  • B. Koopman and G. Zuccon. Dr chatgpt tell me what i want to hear: How different prompts impact health answer correctness. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 15012–15022, 2023.Long paper
  • D.-H. Ngo and B. Koopman. From free-text drug labels to structured medication terminology with bert and gpt. In AMIA Annual Symposium Proceedings, volume 2023, page 540. American Medical Informatics Association, 2023.Long paper
  • A. Nicolson, J. Dowling, and B. Koopman. A concise model for medical image captioning. In CLEF (Working Notes), pages 1611–1619, 2023.Notebook
  • A. Nicolson, J. Dowling, and B. Koopman. e-health csiro at radsum23: Adapting a chest x-ray report generator to multimodal radiology report summarisation. In The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks, pages 545–549, 2023.Notebook
  • A. Nicolson, J. Dowling, and B. Koopman. Improving chest x-ray report generation by leveraging warm starting. Artificial intelligence in medicine, 144:102633, 2023.Journal
  • A. Nicolson, J. Dowling, and B. Koopman. Longitudinal data and a semantic similarity reward for chest x-ray report generation. arXiv preprint arXiv:2307.09758, 2023.Long paper
  • F. Rusak, B. Koopman, N. J. Brown, K. Chu, J. Liu, and A. Nguyen. Catching misdiagnosed limb fractures in the emergency department using cross-institution transfer learning. In Proceedings of the 21st Annual Workshop of the Australasian Language Technology Association, pages 78–87, 2023.Long paper
  • S. Wang, H. Scells, B. Koopman, M. Potthast, and G. Zuccon. Generating natural language queries for more effective systematic review screening prioritisation. In Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region, pages 73–83, 2023.Long paper
  • S. Wang, H. Scells, M. Potthast, B. Koopman, and G. Zuccon. Generating Natural Language Queries for More Effective Systematic Review Screening Prioritisation. In SIGIR-AP, Sept. 2023.Long paper
  • G. Zuccon, B. Koopman, and R. Shaik. Chatgpt hallucinates when attributing answers. In Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region, pages 46–51, 2023.Long paper
  • B. Koopman, A. Mourad, H. Li, A. v. d. Vegt, S. Zhuang, S. Gibson, Y. Dang, D. Lawrence, and G. Zuccon. Agask: an agent to help answer farmer's questions from scientific documents. International Journal on Digital Libraries, June 2023. Journal
  • H. Li, B. Koopman, A. Mourad, and G. Zuccon. Agask: A conversational search agent for answering agricultural questions. In Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining, WSDM '23, Feb 2023. Short paper
  • H. Li, A. Mourad, S. Zhuang, B. Koopman, and G. Zuccon. Pseudo relevance feedback with deep language models and dense retrievers: Successes and pitfalls. ACM Transactions on Information Systems, 41(3):1- 40, 2023.Journal
  • S. Wang, H. Scells, B. Koopman, and G. Zuccon. Can chatgpt write a good boolean query for systematic review literature search? In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2023)., July 2023.Long paper

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2000-