@inproceedings{chhibbar-kalita-2024-automatic,
title = "Automatic Summarization of Long Documents",
author = "Chhibbar, Naman and
Kalita, Jugal",
editor = "Lalitha Devi, Sobha and
Arora, Karunesh",
booktitle = "Proceedings of the 21st International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2024",
address = "AU-KBC Research Centre, Chennai, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2024.icon-1.72/",
pages = "607--615",
abstract = "A vast amount of textual data is added to the internet daily, making utilization and interpretation of such data difficult and cumbersome. As a result, automatic text summarization is crucial for extracting relevant information, saving precious reading time. Although many transformer-based models excel in summarization, they are constrained by their input size, preventing them from processing texts longer than their context size. This study introduces three novel algorithms that allow any LLM to efficiently overcome its input size limitation, effectively utilizing its full potential without any architectural modifications. We test our algorithms on texts with more than 70,000 words, and our experiments show a significant increase in BERTScore with competitive ROUGE scores."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chhibbar-kalita-2024-automatic">
<titleInfo>
<title>Automatic Summarization of Long Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Naman</namePart>
<namePart type="family">Chhibbar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jugal</namePart>
<namePart type="family">Kalita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 21st International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sobha</namePart>
<namePart type="family">Lalitha Devi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karunesh</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">AU-KBC Research Centre, Chennai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A vast amount of textual data is added to the internet daily, making utilization and interpretation of such data difficult and cumbersome. As a result, automatic text summarization is crucial for extracting relevant information, saving precious reading time. Although many transformer-based models excel in summarization, they are constrained by their input size, preventing them from processing texts longer than their context size. This study introduces three novel algorithms that allow any LLM to efficiently overcome its input size limitation, effectively utilizing its full potential without any architectural modifications. We test our algorithms on texts with more than 70,000 words, and our experiments show a significant increase in BERTScore with competitive ROUGE scores.</abstract>
<identifier type="citekey">chhibbar-kalita-2024-automatic</identifier>
<location>
<url>https://aclanthology.org/2024.icon-1.72/</url>
</location>
<part>
<date>2024-12</date>
<extent unit="page">
<start>607</start>
<end>615</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Summarization of Long Documents
%A Chhibbar, Naman
%A Kalita, Jugal
%Y Lalitha Devi, Sobha
%Y Arora, Karunesh
%S Proceedings of the 21st International Conference on Natural Language Processing (ICON)
%D 2024
%8 December
%I NLP Association of India (NLPAI)
%C AU-KBC Research Centre, Chennai, India
%F chhibbar-kalita-2024-automatic
%X A vast amount of textual data is added to the internet daily, making utilization and interpretation of such data difficult and cumbersome. As a result, automatic text summarization is crucial for extracting relevant information, saving precious reading time. Although many transformer-based models excel in summarization, they are constrained by their input size, preventing them from processing texts longer than their context size. This study introduces three novel algorithms that allow any LLM to efficiently overcome its input size limitation, effectively utilizing its full potential without any architectural modifications. We test our algorithms on texts with more than 70,000 words, and our experiments show a significant increase in BERTScore with competitive ROUGE scores.
%U https://aclanthology.org/2024.icon-1.72/
%P 607-615
Markdown (Informal)
[Automatic Summarization of Long Documents](https://aclanthology.org/2024.icon-1.72/) (Chhibbar & Kalita, ICON 2024)
ACL
- Naman Chhibbar and Jugal Kalita. 2024. Automatic Summarization of Long Documents. In Proceedings of the 21st International Conference on Natural Language Processing (ICON), pages 607–615, AU-KBC Research Centre, Chennai, India. NLP Association of India (NLPAI).