Story Grammar Semantic Matching for Literary Study
🤖 AI Summary
Traditional NLP semantic matching relies heavily on lexical co-occurrence, limiting its applicability to interpretable literary analysis. To address this, we propose a semantics modeling approach grounded in explicit story grammar—centering on structured narrative elements such as characters, events, and goals—as core matching features. Methodologically, we develop a manually calibrated annotation schema for story elements, design a label-level semantic matching algorithm, and integrate it with BERT for end-to-end inference. Our key contribution is the first formal integration of story grammar into semantic similarity computation, markedly enhancing transparency, traceability, and humanistic interpretability in cross-text literary analysis. Experiments on epic and prose datasets demonstrate the method’s effectiveness in allusion identification and narrative pattern mining, significantly improving literary scholars’ efficiency and depth in detecting and interpreting latent semantic relationships.
Application Category
📝 Abstract
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.
Problem
Research questions and friction points this paper is trying to address.
Enhance semantic matching for literary texts
Incorporate story structure in NLP analysis
Improve understanding of literary techniques and allusions
Innovation
Methods, ideas, or system contributions that make the work stand out.
BERT language model pipeline
Story element labels
Semantic matching via story structure
🔎 Similar Papers
No similar papers found.
