Abstract: Approaches for determining continuous confidence scores for rule-based negation detection systems overcome deficiencies of existing rule-based negation detection systems that provide only binary output (e.g., negated or not negated). The approaches encompass a pointwise mutual information (PMI)-based approach in which PMI is measured between negation cue words and gold-standard negation annotations in a reference dataset. The approaches also encompass a conditional probability-based approach in which the condition probabilities that gold-standard negations exist in a reference dataset for negation cue words are measured. In both approaches, a form of association between negation cue words and gold-standard negations are measured to provide a more accurate indication of the rule-based system's confidence in a negation determination compared to a binary output.

Abstract: Methods and apparatus for providing metrics for the quality, attributes, and relationships of music including AI-generated music. Music classification and visualization methods are described that involve transforming music files into graphical representations, generating a similarity matrix for the music files using structural similarity techniques, and generating visualizations of the relationships among the music files using multidimensional scaling techniques. Qualitative scoring methods for AI-generated music are described that involve classifying the AI-generated music using a multi-genre classifier, generating a similarity metric for the AI-generated music to other genres using structural similarity techniques and multidimensional scaling techniques, and generating a qualitative score for the music using confidence in the classification in combination with the similarity metric.