Story Grammar Semantic Matching for Literary Study
This addresses the need for more transparent and explanatory semantic matching tools for literary scholars, though it is incremental as it builds on existing BERT models.
The authors tackled the problem of limited analytical power in semantic matching for literary texts by proposing Story Grammar Semantic Matching, which uses story structure labels instead of word co-occurrence, resulting in a method that guides scholars to allusions and similarities across texts.
In Natural Language Processing (NLP), semantic matching algorithms have traditionally relied on the feature of word co-occurrence to measure semantic similarity. While this feature approach has proven valuable in many contexts, its simplistic nature limits its analytical and explanatory power when used to understand literary texts. To address these limitations, we propose a more transparent approach that makes use of story structure and related elements. Using a BERT language model pipeline, we label prose and epic poetry with story element labels and perform semantic matching by only considering these labels as features. This new method, Story Grammar Semantic Matching, guides literary scholars to allusions and other semantic similarities across texts in a way that allows for characterizing patterns and literary technique.