@inproceedings{michel-etal-2024-improving,
title = "Improving Quotation Attribution with Fictional Character Embeddings",
author = "Michel, Gaspard and
Epure, Elena V. and
Hennequin, Romain and
Cerisara, Christophe",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.744",
doi = "10.18653/v1/2024.findings-emnlp.744",
pages = "12723--12735",
abstract = "Humans naturally attribute utterances of direct speech to their speaker in literary works.When attributing quotes, we process contextual information but also access mental representations of characters that we build and revise throughout the narrative. Recent methods to automatically attribute such utterances have explored simulating human logic with deterministic rules or learning new implicit rules with neural networks when processing contextual information.However, these systems inherently lack character representations, which often leads to errors in more challenging examples of attribution: anaphoric and implicit quotes.In this work, we propose to augment a popular quotation attribution system, BookNLP, with character embeddings that encode global stylistic information of characters derived from an off-the-shelf stylometric model, Universal Authorship Representation (UAR).We create DramaCV, a corpus of English drama plays from the 15th to 20th century that we automatically annotate for Authorship Verification of fictional characters utterances, and release two versions of UAR trained on DramaCV, that are tailored for literary characters analysis.Then, through an extensive evaluation on 28 novels, we show that combining BookNLP{'}s contextual information with our proposed global character embeddings improves the identification of speakers for anaphoric and implicit quotes, reaching state-of-the-art performance.Code and data can be found at https://github.com/deezer/character{\_}embeddings{\_}qa.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="michel-etal-2024-improving">
<titleInfo>
<title>Improving Quotation Attribution with Fictional Character Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gaspard</namePart>
<namePart type="family">Michel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="given">V</namePart>
<namePart type="family">Epure</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Romain</namePart>
<namePart type="family">Hennequin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christophe</namePart>
<namePart type="family">Cerisara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Humans naturally attribute utterances of direct speech to their speaker in literary works.When attributing quotes, we process contextual information but also access mental representations of characters that we build and revise throughout the narrative. Recent methods to automatically attribute such utterances have explored simulating human logic with deterministic rules or learning new implicit rules with neural networks when processing contextual information.However, these systems inherently lack character representations, which often leads to errors in more challenging examples of attribution: anaphoric and implicit quotes.In this work, we propose to augment a popular quotation attribution system, BookNLP, with character embeddings that encode global stylistic information of characters derived from an off-the-shelf stylometric model, Universal Authorship Representation (UAR).We create DramaCV, a corpus of English drama plays from the 15th to 20th century that we automatically annotate for Authorship Verification of fictional characters utterances, and release two versions of UAR trained on DramaCV, that are tailored for literary characters analysis.Then, through an extensive evaluation on 28 novels, we show that combining BookNLP’s contextual information with our proposed global character embeddings improves the identification of speakers for anaphoric and implicit quotes, reaching state-of-the-art performance.Code and data can be found at https://github.com/deezer/character_embeddings_qa.</abstract>
<identifier type="citekey">michel-etal-2024-improving</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.744</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.744</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>12723</start>
<end>12735</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Quotation Attribution with Fictional Character Embeddings
%A Michel, Gaspard
%A Epure, Elena V.
%A Hennequin, Romain
%A Cerisara, Christophe
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F michel-etal-2024-improving
%X Humans naturally attribute utterances of direct speech to their speaker in literary works.When attributing quotes, we process contextual information but also access mental representations of characters that we build and revise throughout the narrative. Recent methods to automatically attribute such utterances have explored simulating human logic with deterministic rules or learning new implicit rules with neural networks when processing contextual information.However, these systems inherently lack character representations, which often leads to errors in more challenging examples of attribution: anaphoric and implicit quotes.In this work, we propose to augment a popular quotation attribution system, BookNLP, with character embeddings that encode global stylistic information of characters derived from an off-the-shelf stylometric model, Universal Authorship Representation (UAR).We create DramaCV, a corpus of English drama plays from the 15th to 20th century that we automatically annotate for Authorship Verification of fictional characters utterances, and release two versions of UAR trained on DramaCV, that are tailored for literary characters analysis.Then, through an extensive evaluation on 28 novels, we show that combining BookNLP’s contextual information with our proposed global character embeddings improves the identification of speakers for anaphoric and implicit quotes, reaching state-of-the-art performance.Code and data can be found at https://github.com/deezer/character_embeddings_qa.
%R 10.18653/v1/2024.findings-emnlp.744
%U https://aclanthology.org/2024.findings-emnlp.744
%U https://doi.org/10.18653/v1/2024.findings-emnlp.744
%P 12723-12735
Markdown (Informal)
[Improving Quotation Attribution with Fictional Character Embeddings](https://aclanthology.org/2024.findings-emnlp.744) (Michel et al., Findings 2024)
ACL