<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bindal-etal-2026-interpretable">
    <titleInfo>
        <title>An Interpretable Linguistically-Grounded Analysis of Scene Saliency in Movie Screenplays</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Uday</namePart>
        <namePart type="family">Bindal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ishaan</namePart>
        <namePart type="family">Karan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Manan</namePart>
        <namePart type="family">Garg</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ekansh</namePart>
        <namePart type="family">Goyal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rahul</namePart>
        <namePart type="family">Mishra</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rajakrishnan</namePart>
        <namePart type="given">P</namePart>
        <namePart type="family">Rajkumar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>We investigate the factors affecting salience in movie screenplay by posing two research questions: 1. Does Uniform Information Density (UID) predict salient scenes? 2. 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. Perscene 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>
    <identifier type="citekey">bindal-etal-2026-interpretable</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.2391/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>54364</start>
            <end>54387</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T An Interpretable Linguistically-Grounded Analysis of Scene Saliency in Movie Screenplays
%A Bindal, Uday
%A Karan, Ishaan
%A Garg, Manan
%A Goyal, Ekansh
%A Mishra, Rahul
%A Rajkumar, Rajakrishnan P.
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F bindal-etal-2026-interpretable
%X We investigate the factors affecting salience in movie screenplay by posing two research questions: 1. Does Uniform Information Density (UID) predict salient scenes? 2. 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. Perscene 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.
%U https://aclanthology.org/2026.emnlp-main.2391/
%P 54364-54387

Markdown (Informal)

[An Interpretable Linguistically-Grounded Analysis of Scene Saliency in Movie Screenplays](https://aclanthology.org/2026.emnlp-main.2391/) (Bindal et al., EMNLP 2026)

• An Interpretable Linguistically-Grounded Analysis of Scene Saliency in Movie Screenplays (Bindal et al., EMNLP 2026)

ACL

• Uday Bindal, Ishaan Karan, Manan Garg, Ekansh Goyal, Rahul Mishra, and Rajakrishnan P Rajkumar. 2026. An Interpretable Linguistically-Grounded Analysis of Scene Saliency in Movie Screenplays. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 54364–54387, Budapest, Hungary. Association for Computational Linguistics.