Corpus ID: 1335600

Continuous Active Learning for TAR

  title={Continuous Active Learning for TAR},
  author={Maura R. Grossman and Gordon V. Cormack},
The vast array of technology-assisted review (TAR) tools available in the marketplace, along with their associated jargon, can seem daunting to counsel. But using TAR in litigation and regulatory matters need not be. By implementing a continuous active learning (CAL) protocol, with a TAR tool that uses a state-of-the-art machine-learning algorithm, responding parties can quickly and easily identify substantially all of the relevant documents in a collection and minimize the potential for… Expand

Figures from this paper

Participation in TREC 2020 COVID Track Using Continuous Active Learning
All five rounds of the TREC 2020 COVID Track challenged participants to perform a classic ad-hoc search task on the new data collection CORD-19, and the solution addressed this challenge by applying the Continuous Active Learning model (CAL) and its variations. Expand
Discovering Play Store Reviews Related to Specific Android App Issues
This thesis attempts to devise a framework that would allow developers to define topics related to app issues at any time, and with minimal effort, discover as many reviews related to the issue as possible and shows that developers can discover relevant information during the process of training the model. Expand
Evaluating visual analytics for text information retrieval
Observational studies on VA-supported text information retrieval concluded that most users have a very positive view of the system's usability and its ability to facilitate their retrieval tasks, and that a proper introduction to the role of the interface elements is important and that conveying the underlying conceptual model and its limitations can be difficult. Expand
TRIVIR: A Visualization System to Support Document Retrieval with High Recall
TRIVIR is a novel interactive visualization tool powered by an Information Retrieval (IR) engine that implements an active learning protocol to support IR with high recall that integrates multiple graphical views in order to assist the user identifying the relevant documents in a collection. Expand