@inproceedings{han-etal-2021-fantasycoref,
title = "{F}antasy{C}oref: Coreference Resolution on Fantasy Literature Through Omniscient Writer{'}s Point of View",
author = "Han, Sooyoun and
Seo, Sumin and
Kang, Minji and
Kim, Jongin and
Choi, Nayoung and
Song, Min and
Choi, Jinho D.",
editor = "Ogrodniczuk, Maciej and
Pradhan, Sameer and
Poesio, Massimo and
Grishina, Yulia and
Ng, Vincent",
booktitle = "Proceedings of the Fourth Workshop on Computational Models of Reference, Anaphora and Coreference",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.crac-1.3",
doi = "10.18653/v1/2021.crac-1.3",
pages = "24--35",
abstract = "This paper presents a new corpus and annotation guideline for a novel coreference resolution task on fictional texts, and analyzes its unique characteristics. FantasyCoref contains 211 stories of Grimms{'} Fairy Tales and 3 other fantasy literature annotated in the omniscient writer{'}s point of view (OWV) to handle distinctive aspects in this genre. This task is more challenging than general coreference resolution in two ways. First, documents in our corpus are 2.5 times longer than the ones in OntoNotes, raising a new layer of difficulty in resolving long-distant referents. Second, annotation of literary styles and concepts raise several issues which are not sufficiently addressed in the existing annotation guidelines. Hence, considerations on such issues and the concept of OWV are necessary to achieve high inter-annotator agreement (IAA) in coreference resolution of fictional texts. We carefully conduct annotation tasks in four stages to ensure the quality of our annotation. As a result, a high IAA score of 87{\%} is achieved using the standard coreference evaluation metric. Finally, state-of-the-art coreference resolution approaches are evaluated on our corpus. After training with our annotated dataset, there was a 2.59{\%} and 3.06{\%} improvement over the model trained on the OntoNotes dataset. Also, we observe that the portion of errors specific to fictional texts declines after the training.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="han-etal-2021-fantasycoref">
<titleInfo>
<title>FantasyCoref: Coreference Resolution on Fantasy Literature Through Omniscient Writer’s Point of View</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sooyoun</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sumin</namePart>
<namePart type="family">Seo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minji</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jongin</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nayoung</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinho</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Computational Models of Reference, Anaphora and Coreference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maciej</namePart>
<namePart type="family">Ogrodniczuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sameer</namePart>
<namePart type="family">Pradhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Massimo</namePart>
<namePart type="family">Poesio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulia</namePart>
<namePart type="family">Grishina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a new corpus and annotation guideline for a novel coreference resolution task on fictional texts, and analyzes its unique characteristics. FantasyCoref contains 211 stories of Grimms’ Fairy Tales and 3 other fantasy literature annotated in the omniscient writer’s point of view (OWV) to handle distinctive aspects in this genre. This task is more challenging than general coreference resolution in two ways. First, documents in our corpus are 2.5 times longer than the ones in OntoNotes, raising a new layer of difficulty in resolving long-distant referents. Second, annotation of literary styles and concepts raise several issues which are not sufficiently addressed in the existing annotation guidelines. Hence, considerations on such issues and the concept of OWV are necessary to achieve high inter-annotator agreement (IAA) in coreference resolution of fictional texts. We carefully conduct annotation tasks in four stages to ensure the quality of our annotation. As a result, a high IAA score of 87% is achieved using the standard coreference evaluation metric. Finally, state-of-the-art coreference resolution approaches are evaluated on our corpus. After training with our annotated dataset, there was a 2.59% and 3.06% improvement over the model trained on the OntoNotes dataset. Also, we observe that the portion of errors specific to fictional texts declines after the training.</abstract>
<identifier type="citekey">han-etal-2021-fantasycoref</identifier>
<identifier type="doi">10.18653/v1/2021.crac-1.3</identifier>
<location>
<url>https://aclanthology.org/2021.crac-1.3</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>24</start>
<end>35</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FantasyCoref: Coreference Resolution on Fantasy Literature Through Omniscient Writer’s Point of View
%A Han, Sooyoun
%A Seo, Sumin
%A Kang, Minji
%A Kim, Jongin
%A Choi, Nayoung
%A Song, Min
%A Choi, Jinho D.
%Y Ogrodniczuk, Maciej
%Y Pradhan, Sameer
%Y Poesio, Massimo
%Y Grishina, Yulia
%Y Ng, Vincent
%S Proceedings of the Fourth Workshop on Computational Models of Reference, Anaphora and Coreference
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F han-etal-2021-fantasycoref
%X This paper presents a new corpus and annotation guideline for a novel coreference resolution task on fictional texts, and analyzes its unique characteristics. FantasyCoref contains 211 stories of Grimms’ Fairy Tales and 3 other fantasy literature annotated in the omniscient writer’s point of view (OWV) to handle distinctive aspects in this genre. This task is more challenging than general coreference resolution in two ways. First, documents in our corpus are 2.5 times longer than the ones in OntoNotes, raising a new layer of difficulty in resolving long-distant referents. Second, annotation of literary styles and concepts raise several issues which are not sufficiently addressed in the existing annotation guidelines. Hence, considerations on such issues and the concept of OWV are necessary to achieve high inter-annotator agreement (IAA) in coreference resolution of fictional texts. We carefully conduct annotation tasks in four stages to ensure the quality of our annotation. As a result, a high IAA score of 87% is achieved using the standard coreference evaluation metric. Finally, state-of-the-art coreference resolution approaches are evaluated on our corpus. After training with our annotated dataset, there was a 2.59% and 3.06% improvement over the model trained on the OntoNotes dataset. Also, we observe that the portion of errors specific to fictional texts declines after the training.
%R 10.18653/v1/2021.crac-1.3
%U https://aclanthology.org/2021.crac-1.3
%U https://doi.org/10.18653/v1/2021.crac-1.3
%P 24-35
Markdown (Informal)
[FantasyCoref: Coreference Resolution on Fantasy Literature Through Omniscient Writer’s Point of View](https://aclanthology.org/2021.crac-1.3) (Han et al., CRAC 2021)
ACL
- Sooyoun Han, Sumin Seo, Minji Kang, Jongin Kim, Nayoung Choi, Min Song, and Jinho D. Choi. 2021. FantasyCoref: Coreference Resolution on Fantasy Literature Through Omniscient Writer’s Point of View. In Proceedings of the Fourth Workshop on Computational Models of Reference, Anaphora and Coreference, pages 24–35, Punta Cana, Dominican Republic. Association for Computational Linguistics.