S
Sarvnaz Karimi
Researcher at Commonwealth Scientific and Industrial Research Organisation
Publications - 108
Citations - 2318
Sarvnaz Karimi is an academic researcher from Commonwealth Scientific and Industrial Research Organisation. The author has contributed to research in topics: Computer science & Transliteration. The author has an hindex of 22, co-authored 94 publications receiving 1842 citations. Previous affiliations of Sarvnaz Karimi include University of Melbourne & RMIT University.
Papers
More filters
Proceedings Article
Corpus Effects on the Evaluation of Automated Transliteration Systems
TL;DR: It is found that the word accuracy of automated transliteration systems can vary by up to 30% depending on the corpus on which they are run, and that although absolute word accuracy metrics may not translate across corpora, the relative rankings of system performance remains stable across differing corpora.
Proceedings ArticleDOI
An Experimentation Platform for Precision Medicine
TL;DR: An on-line system which enables experimentation in search for precision medicine within the framework provided by the TREC Precision Medicine (PM) track is presented and some of the most promising gene mention expansion methods, as well as learning-to-rank using neural networks are provided.
Proceedings Article
Parallel Duplicate Detection in Adverse Drug Reaction Databases with Spark.
Chen Wang,Sarvnaz Karimi +1 more
TL;DR: A scalable duplicate detection method built on top of Spark that uses the kNN (k nearest neighbors) classifier to identify labelled report pairs that are most useful for classifying new report pairs and a method to minimize the crosscluster kNN search.
Proceedings ArticleDOI
A2A: Benchmark Your Clinical Decision Support Search
TL;DR: This work developed a platform to facilitate experimentation and hypothesis testing for information retrieval researchers working on this topic and provides a large range of query and document processing techniques that are explored in the biomedical search domain.
Journal ArticleDOI
Beyond mean rating: Probabilistic aggregation of star ratings based on helpfulness
TL;DR: This work proposes probabilistic aggregation models for review ratings based on the Dirichlet distribution to combat data sparsity in reviews and proposes to exploit the “helpfulness” social information and time to filter noisy reviews and effectively aggregate ratings to compute the consensus opinion.