An Evaluation of Story Grammars*

Abstract

We evaluate the “story grammar” approach to story understanding from three perspectives. We first examine the formal properties of the grammars and find only one to be formally adequate. We next evaluate the grammars empirically by asking whether they generate all simple stories and whether they generate only stories. We find many stories that they do not generate and one major class of nonstory that they do generate. We also evaluate the grammars' potential as comprehension models and find that they would add nothing to semantic models that focus on the story content. Hence we advocate a story content oriented approach to studying story understanding instead of the structural story grammar approach.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 222 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.