@inproceedings{bhat-etal-2021-hierarchical,
title = "Hierarchical Encoders for Modeling and Interpreting Screenplays",
author = "Bhat, Gayatri and
Saluja, Avneesh and
Dye, Melody and
Florjanczyk, Jan",
editor = "Akoury, Nader and
Brahman, Faeze and
Chaturvedi, Snigdha and
Clark, Elizabeth and
Iyyer, Mohit and
Martin, Lara J.",
booktitle = "Proceedings of the Third Workshop on Narrative Understanding",
month = jun,
year = "2021",
address = "Virtual",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.nuse-1.1",
doi = "10.18653/v1/2021.nuse-1.1",
pages = "1--12",
abstract = "While natural language understanding of long-form documents remains an open challenge, such documents often contain structural information that can inform the design of models encoding them. Movie scripts are an example of such richly structured text {--} scripts are segmented into scenes, which decompose into dialogue and descriptive components. In this work, we propose a neural architecture to encode this structure, which performs robustly on two multi-label tag classification tasks without using handcrafted features. We add a layer of insight by augmenting the encoder with an unsupervised {`}interpretability{'} module, which can be used to extract and visualize narrative trajectories. Though this work specifically tackles screenplays, we discuss how the underlying approach can be generalized to a range of structured documents.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhat-etal-2021-hierarchical">
<titleInfo>
<title>Hierarchical Encoders for Modeling and Interpreting Screenplays</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gayatri</namePart>
<namePart type="family">Bhat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Avneesh</namePart>
<namePart type="family">Saluja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Melody</namePart>
<namePart type="family">Dye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Florjanczyk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Narrative Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nader</namePart>
<namePart type="family">Akoury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Faeze</namePart>
<namePart type="family">Brahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Snigdha</namePart>
<namePart type="family">Chaturvedi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Clark</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Iyyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lara</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Martin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Virtual</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While natural language understanding of long-form documents remains an open challenge, such documents often contain structural information that can inform the design of models encoding them. Movie scripts are an example of such richly structured text – scripts are segmented into scenes, which decompose into dialogue and descriptive components. In this work, we propose a neural architecture to encode this structure, which performs robustly on two multi-label tag classification tasks without using handcrafted features. We add a layer of insight by augmenting the encoder with an unsupervised ‘interpretability’ module, which can be used to extract and visualize narrative trajectories. Though this work specifically tackles screenplays, we discuss how the underlying approach can be generalized to a range of structured documents.</abstract>
<identifier type="citekey">bhat-etal-2021-hierarchical</identifier>
<identifier type="doi">10.18653/v1/2021.nuse-1.1</identifier>
<location>
<url>https://aclanthology.org/2021.nuse-1.1</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>1</start>
<end>12</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hierarchical Encoders for Modeling and Interpreting Screenplays
%A Bhat, Gayatri
%A Saluja, Avneesh
%A Dye, Melody
%A Florjanczyk, Jan
%Y Akoury, Nader
%Y Brahman, Faeze
%Y Chaturvedi, Snigdha
%Y Clark, Elizabeth
%Y Iyyer, Mohit
%Y Martin, Lara J.
%S Proceedings of the Third Workshop on Narrative Understanding
%D 2021
%8 June
%I Association for Computational Linguistics
%C Virtual
%F bhat-etal-2021-hierarchical
%X While natural language understanding of long-form documents remains an open challenge, such documents often contain structural information that can inform the design of models encoding them. Movie scripts are an example of such richly structured text – scripts are segmented into scenes, which decompose into dialogue and descriptive components. In this work, we propose a neural architecture to encode this structure, which performs robustly on two multi-label tag classification tasks without using handcrafted features. We add a layer of insight by augmenting the encoder with an unsupervised ‘interpretability’ module, which can be used to extract and visualize narrative trajectories. Though this work specifically tackles screenplays, we discuss how the underlying approach can be generalized to a range of structured documents.
%R 10.18653/v1/2021.nuse-1.1
%U https://aclanthology.org/2021.nuse-1.1
%U https://doi.org/10.18653/v1/2021.nuse-1.1
%P 1-12
Markdown (Informal)
[Hierarchical Encoders for Modeling and Interpreting Screenplays](https://aclanthology.org/2021.nuse-1.1) (Bhat et al., NUSE-WNU 2021)
ACL