analiza aiqbench
This research applies linguistically-grounded models and frozen BERT encoders to analyze scene salience in screenplays, offering new insights into how information density and specific linguistic features drive narrative focus. By fusing explicit linguistic properties with neural representations, the study demonstrates improved recall for identifying key scenes compared to standard semantic baselines. The work represents a significant contribution to NLP applications in creative text analysis and computational narratology.
An Interpretable Linguistically-Grounded Analysis of Scene Saliency in Movie Screenplays
arXiv:2610.15544v1 Announce Type: new Abstract: We investigate the factors affecting salience in movie screenplay by posing two research questions: 1. {\em Does Uniform Information Density (UID) predict salient scenes?} 2. {\em What other linguistic properties distinguish salient scenes from non-salient background?} We answer both questions through a controlled corpus study on the MENSA corpus, paired with a Linguistically-Grounded Salience Model (LGSM), a dual-stream classifier that fuses a frozen BERT encoder with explicit linguistic features through adaptive gating. The UID picture is layered in long-form discourse. Per-scene UID summaries carry no independent signal once length is controlled, but at the token level salient scenes match non-salient material in the bulk while specifically suppressing the rarest, hardest-to-predict tokens in the upper tail. UID therefore lives at the within-scene token level rather than as a per-scene aggregate. Salient scenes also show a moderate and sustained cast of central characters (following an inverted-U pattern), strong third-person usage, syntactically simpler language, and more abstract vocabulary about motivation and conflict. LGSM exploits this signature and improves recall on salient scenes over a strong semantic baseline while yielding better downstream summaries.
Abstract:We investigate the factors affecting salience in movie screenplay by posing two research questions: 1. {\em Does Uniform Information Density (UID) predict salient scenes?} 2. {\em What other linguistic properties distinguish salient scenes from non-salient background?} We answer both questions through a controlled corpus study on the MENSA corpus, paired with a Linguistically-Grounded Salience Model (LGSM), a dual-stream classifier that fuses a frozen BERT encoder with explicit linguistic features through adaptive gating. The UID picture is layered in long-form discourse. Per-scene UID summaries carry no independent signal once length is controlled, but at the token level salient scenes match non-salient material in the bulk while specifically suppressing the rarest, hardest-to-predict tokens in the upper tail. UID therefore lives at the within-scene token level rather than as a per-scene aggregate. Salient scenes also show a moderate and sustained cast of central characters (following an inverted-U pattern), strong third-person usage, syntactically simpler language, and more abstract vocabulary about motivation and conflict. LGSM exploits this signature and improves recall on salient scenes over a strong semantic baseline while yielding better downstream summaries.
Computation and Language (cs.CL)
arXiv:2610.15544 [cs.CL]
(or arXiv:2610.15544v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2610.15544 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 274 cuvinte
Subiecte conexe
The Shape of Power: A Multilingual Framework for Social Power Reasoning in Dialogues
arXiv · 1 sept. 2026
Why do models task game?
AI Alignment Forum · 6 aug. 2026
The director of Fjord takes the ‘risky position’ of moderator
The Verge · 10 oct. 2026
KANEx: Translating Kolmogorov-Arnold Networks' Interpretability to Medical Explainability
arXiv · 28 iul. 2026