Landing Propp in Interaction Space: First Steps Toward Scalable Open Domain Narrative Analysis With Predication-based Semantic Indexing

• DOI: 10.13140/rg.2.1.1893.6488
• Publication Date: 2015-01-01
• Authors: Malec, S.; Darányi, Sándor; Widdows, D.; Cohen, T.
• Keywords: Vector Symbolic Architectures; distributional semantics; formal models; predication based semantic indexing; Etnologi; narrative analysis; semantic space; Other Computer and Information Science; folktales; Annan data- och informationsvetenskap; Propp; Ethnology

In this paper, we explore the possibility of applying high-dimensionalvector representations of concept-relation-concept triplets, which have been successfullyapplied to model a small set of relationship types in the biomedicaldomain, to the task of modeling folk tales. In doing so, our ultimate aim is todevelop representations of narratives through which their underlying structurecan be compared. The current paper describes our progress toward this aim, withemphasis on addressing the technical challenges involved in moving from therelatively constrained set of relations that have been extracted from biomedicaltext to the much larger set of unnormalized relations that have been extractedfrom the open domain. A toy example using graded vectors demonstrates that ourapproach will be feasible once more material will be added to the test collection.