Evaluation Evaluation a Monte Carlo study
This addresses the issue of misleading system improvements in NLP for researchers and practitioners, though it is incremental in refining evaluation methodologies.
The paper tackles the problem of biased evaluation measures in NLP, such as Recall and Precision, by analyzing and comparing them with unbiased alternatives like Cohen Kappa and Powers Informedness, using theoretical analysis and Monte Carlo simulations to characterize their relationships.
Over the last decade there has been increasing concern about the biases embodied in traditional evaluation methods for Natural Language Processing/Learning, particularly methods borrowed from Information Retrieval. Without knowledge of the Bias and Prevalence of the contingency being tested, or equivalently the expectation due to chance, the simple conditional probabilities Recall, Precision and Accuracy are not meaningful as evaluation measures, either individually or in combinations such as F-factor. The existence of bias in NLP measures leads to the 'improvement' of systems by increasing their bias, such as the practice of improving tagging and parsing scores by using most common value (e.g. water is always a Noun) rather than the attempting to discover the correct one. The measures Cohen Kappa and Powers Informedness are discussed as unbiased alternative to Recall and related to the psychologically significant measure DeltaP. In this paper we will analyze both biased and unbiased measures theoretically, characterizing the precise relationship between all these measures as well as evaluating the evaluation measures themselves empirically using a Monte Carlo simulation.