Adapting NLP tools and frame-semantic resources for the semantic analysis of ritual descriptions
In this paper we investigate the use of standard natural language processing (NLP) tools and annotation methods for processing linguistic data from ritual science, which is concerned with the study of structure and variance of rituals. The work is embedded in an interdisciplinary project that addresses this study by applying empirical and quantitative computational linguistic analysis techniques to ritual descriptions from Indian rituals. We present motivation and prospects of such a computational approach to ritual structure research and sketch the overall project research plan. In particular, we motivate the choice of frame semantics as a theoretical framework for the semantic analysis of rituals. We discuss the special characteristics of the textual data and examine several domain adaptation strategies in order to use standard NLP resources and tools on the ritual domain. We also report on our workflows and methods for semi-automatic semantic annotation, which is used as a basis for the extraction of event chains. We close with some preliminary investigations on how to uncover regularities and differences of rituals.