The phrase "automatic metric" is correct and usable in written English.
It can be used in contexts related to measurement systems, data analysis, or performance evaluation where metrics are generated automatically.
Example: "The software provides an automatic metric for tracking user engagement over time."
Alternatives: "automated measurement" or "self-generating metric".
The resulting metric, based on support vector machines, is shown to significantly improve upon current automatic metrics, increasing correlation with human judgments at the sentence level halfway toward that achieved by an independent human evaluator.
In a national representative sample of non-institutional population in England, 21.5% of subjects aged 40 79 years were on-site diagnosed with grade 1 hypertension using automatic oscillo-metric devices [ 29].
In this paper we examine the applicability of spectral graph partitioning techniques to the automatic generation of metric submaps by establishing groups in the sequence of observations gathered by the robot.
In particular, to calculate the threshold for the throughput metric, automatic learning techniques can be applied to the datasets, replacing the sensitivity analysis.
Wristbands that measure your skin conductivity, chest straps that measure your heart rate, sensors that measure the pressure you place on your keypad and mouse, all working to devise an "automatic interruptibility measure"—a metric of how busy (or not) you are from moment to moment and how available you are for conversation.
As noted in the "Automatic experiment" section, the metric SP measures the dispersion between the Pareto front solutions.
ROUGE compares the quality of a computer-generated summary versus a human-generated summary and is a widely accepted metric for automatic evaluation of summarization tasks (DUC 2004-2007 and TAC 2008-2010).
The adoption of an objective model allows to determine the parameters of the ITU metric in an automatic way, without requiring expensive and costly subjective experiments.
In addition, a novel criterion is proposed to control the growing process for ensured geometric integrity and automatic boundary detection with a non-metric threshold.
As an application, the proposed metric is further used for automatic parameter selection in image deblocking algorithms.
