@inproceedings{chowdhury-etal-2021-unsupervised,
title = "Unsupervised Abstractive Summarization of {B}engali Text Documents",
author = "Chowdhury, Radia Rayan and
Nayeem, Mir Tafseer and
Mim, Tahsin Tasnim and
Chowdhury, Md. Saifur Rahman and
Jannat, Taufiqul",
editor = "Merlo, Paola and
Tiedemann, Jorg and
Tsarfaty, Reut",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-main.224",
doi = "10.18653/v1/2021.eacl-main.224",
pages = "2612--2619",
abstract = "Abstractive summarization systems generally rely on large collections of document-summary pairs. However, the performance of abstractive systems remains a challenge due to the unavailability of the parallel data for low-resource languages like Bengali. To overcome this problem, we propose a graph-based unsupervised abstractive summarization system in the single-document setting for Bengali text documents, which requires only a Part-Of-Speech (POS) tagger and a pre-trained language model trained on Bengali texts. We also provide a human-annotated dataset with document-summary pairs to evaluate our abstractive model and to support the comparison of future abstractive summarization systems of the Bengali Language. We conduct experiments on this dataset and compare our system with several well-established unsupervised extractive summarization systems. Our unsupervised abstractive summarization model outperforms the baselines without being exposed to any human-annotated reference summaries.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chowdhury-etal-2021-unsupervised">
<titleInfo>
<title>Unsupervised Abstractive Summarization of Bengali Text Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Radia</namePart>
<namePart type="given">Rayan</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mir</namePart>
<namePart type="given">Tafseer</namePart>
<namePart type="family">Nayeem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tahsin</namePart>
<namePart type="given">Tasnim</namePart>
<namePart type="family">Mim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Saifur</namePart>
<namePart type="given">Rahman</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taufiqul</namePart>
<namePart type="family">Jannat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Merlo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Abstractive summarization systems generally rely on large collections of document-summary pairs. However, the performance of abstractive systems remains a challenge due to the unavailability of the parallel data for low-resource languages like Bengali. To overcome this problem, we propose a graph-based unsupervised abstractive summarization system in the single-document setting for Bengali text documents, which requires only a Part-Of-Speech (POS) tagger and a pre-trained language model trained on Bengali texts. We also provide a human-annotated dataset with document-summary pairs to evaluate our abstractive model and to support the comparison of future abstractive summarization systems of the Bengali Language. We conduct experiments on this dataset and compare our system with several well-established unsupervised extractive summarization systems. Our unsupervised abstractive summarization model outperforms the baselines without being exposed to any human-annotated reference summaries.</abstract>
<identifier type="citekey">chowdhury-etal-2021-unsupervised</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.224</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.224</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>2612</start>
<end>2619</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Abstractive Summarization of Bengali Text Documents
%A Chowdhury, Radia Rayan
%A Nayeem, Mir Tafseer
%A Mim, Tahsin Tasnim
%A Chowdhury, Md. Saifur Rahman
%A Jannat, Taufiqul
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F chowdhury-etal-2021-unsupervised
%X Abstractive summarization systems generally rely on large collections of document-summary pairs. However, the performance of abstractive systems remains a challenge due to the unavailability of the parallel data for low-resource languages like Bengali. To overcome this problem, we propose a graph-based unsupervised abstractive summarization system in the single-document setting for Bengali text documents, which requires only a Part-Of-Speech (POS) tagger and a pre-trained language model trained on Bengali texts. We also provide a human-annotated dataset with document-summary pairs to evaluate our abstractive model and to support the comparison of future abstractive summarization systems of the Bengali Language. We conduct experiments on this dataset and compare our system with several well-established unsupervised extractive summarization systems. Our unsupervised abstractive summarization model outperforms the baselines without being exposed to any human-annotated reference summaries.
%R 10.18653/v1/2021.eacl-main.224
%U https://aclanthology.org/2021.eacl-main.224
%U https://doi.org/10.18653/v1/2021.eacl-main.224
%P 2612-2619
Markdown (Informal)
[Unsupervised Abstractive Summarization of Bengali Text Documents](https://aclanthology.org/2021.eacl-main.224) (Chowdhury et al., EACL 2021)
ACL
- Radia Rayan Chowdhury, Mir Tafseer Nayeem, Tahsin Tasnim Mim, Md. Saifur Rahman Chowdhury, and Taufiqul Jannat. 2021. Unsupervised Abstractive Summarization of Bengali Text Documents. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 2612–2619, Online. Association for Computational Linguistics.