TARexp: A Python Framework for Technology-Assisted Review Experiments
This framework addresses the problem of accessibility for researchers in TAR, an industrial application of IR and ML, by simplifying software and workflow complexity, though it is incremental as it builds on past open-source efforts.
The authors tackled the complexity barrier in technology-assisted review (TAR) research by developing TARexp, an open-source Python framework that enables experiments on TAR algorithms, featuring declarative workflows and reference implementations.
Technology-assisted review (TAR) is an important industrial application of information retrieval (IR) and machine learning (ML). While a small TAR research community exists, the complexity of TAR software and workflows is a major barrier to entry. Drawing on past open source TAR efforts, as well as design patterns from the IR and ML open source software, we present an open source Python framework for conducting experiments on TAR algorithms. Key characteristics of this framework are declarative representations of workflows and experiment plans, the ability for components to play variable numbers of workflow roles, and state maintenance and restart capabilities. Users can draw on reference implementations of standard TAR algorithms while incorporating novel components to explore their research interests. The framework is available at https://github.com/eugene-yang/tarexp.