@inproceedings{pial-skiena-2023-gnat,
title = "{GNAT}: A General Narrative Alignment Tool",
author = "Pial, Tanzir and
Skiena, Steven",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.904",
doi = "10.18653/v1/2023.emnlp-main.904",
pages = "14636--14652",
abstract = "Algorithmic sequence alignment identifies similar segments shared between pairs of documents, and is fundamental to many NLP tasks. But it is difficult to recognize similarities between distant versions of narratives such as translations and retellings, particularly for summaries and abridgements which are much shorter than the original novels. We develop a general approach to narrative alignment coupling the Smith-Waterman algorithm from bioinformatics with modern text similarity metrics. We show that the background of alignment scores fits a Gumbel distribution, enabling us to define rigorous p-values on the significance of any alignment. We apply and evaluate our general narrative alignment tool (GNAT) on four distinct problem domains differing greatly in both the relative and absolute length of documents, namely summary-to-book alignment, translated book alignment, short story alignment, and plagiarism detection{---}demonstrating the power and performance of our methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pial-skiena-2023-gnat">
<titleInfo>
<title>GNAT: A General Narrative Alignment Tool</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tanzir</namePart>
<namePart type="family">Pial</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Skiena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Algorithmic sequence alignment identifies similar segments shared between pairs of documents, and is fundamental to many NLP tasks. But it is difficult to recognize similarities between distant versions of narratives such as translations and retellings, particularly for summaries and abridgements which are much shorter than the original novels. We develop a general approach to narrative alignment coupling the Smith-Waterman algorithm from bioinformatics with modern text similarity metrics. We show that the background of alignment scores fits a Gumbel distribution, enabling us to define rigorous p-values on the significance of any alignment. We apply and evaluate our general narrative alignment tool (GNAT) on four distinct problem domains differing greatly in both the relative and absolute length of documents, namely summary-to-book alignment, translated book alignment, short story alignment, and plagiarism detection—demonstrating the power and performance of our methods.</abstract>
<identifier type="citekey">pial-skiena-2023-gnat</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.904</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.904</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>14636</start>
<end>14652</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GNAT: A General Narrative Alignment Tool
%A Pial, Tanzir
%A Skiena, Steven
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F pial-skiena-2023-gnat
%X Algorithmic sequence alignment identifies similar segments shared between pairs of documents, and is fundamental to many NLP tasks. But it is difficult to recognize similarities between distant versions of narratives such as translations and retellings, particularly for summaries and abridgements which are much shorter than the original novels. We develop a general approach to narrative alignment coupling the Smith-Waterman algorithm from bioinformatics with modern text similarity metrics. We show that the background of alignment scores fits a Gumbel distribution, enabling us to define rigorous p-values on the significance of any alignment. We apply and evaluate our general narrative alignment tool (GNAT) on four distinct problem domains differing greatly in both the relative and absolute length of documents, namely summary-to-book alignment, translated book alignment, short story alignment, and plagiarism detection—demonstrating the power and performance of our methods.
%R 10.18653/v1/2023.emnlp-main.904
%U https://aclanthology.org/2023.emnlp-main.904
%U https://doi.org/10.18653/v1/2023.emnlp-main.904
%P 14636-14652
Markdown (Informal)
[GNAT: A General Narrative Alignment Tool](https://aclanthology.org/2023.emnlp-main.904) (Pial & Skiena, EMNLP 2023)
ACL
- Tanzir Pial and Steven Skiena. 2023. GNAT: A General Narrative Alignment Tool. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 14636–14652, Singapore. Association for Computational Linguistics.