@inproceedings{johner-etal-2021-error,
title = "Error Analysis of using {BART} for Multi-Document Summarization: A Study for {E}nglish and {G}erman Language",
author = "Johner, Timo and
Jana, Abhik and
Biemann, Chris",
editor = "Dobnik, Simon and
{\O}vrelid, Lilja",
booktitle = "Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)",
month = may # " 31--2 " # jun,
year = "2021",
address = "Reykjavik, Iceland (Online)",
publisher = {Link{\"o}ping University Electronic Press, Sweden},
url = "https://aclanthology.org/2021.nodalida-main.43/",
pages = "391--397",
abstract = "Recent research using pre-trained language models for multi-document summarization task lacks deep investigation of potential erroneous cases and their possible application on other languages. In this work, we apply a pre-trained language model (BART) for multi-document summarization (MDS) task using both fine-tuning and without fine-tuning. We use two English datasets and one German dataset for this study. First, we reproduce the multi-document summaries for English language by following one of the recent studies. Next, we show the applicability of the model to German language by achieving state-of-the-art performance on German MDS. We perform an in-depth error analysis of the followed approach for both languages, which leads us to identifying most notable errors, from made-up facts and topic delimitation, and quantifying the amount of extractiveness."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="johner-etal-2021-error">
<titleInfo>
<title>Error Analysis of using BART for Multi-Document Summarization: A Study for English and German Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Timo</namePart>
<namePart type="family">Johner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhik</namePart>
<namePart type="family">Jana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Biemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-may 31–2 jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lilja</namePart>
<namePart type="family">Øvrelid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Linköping University Electronic Press, Sweden</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent research using pre-trained language models for multi-document summarization task lacks deep investigation of potential erroneous cases and their possible application on other languages. In this work, we apply a pre-trained language model (BART) for multi-document summarization (MDS) task using both fine-tuning and without fine-tuning. We use two English datasets and one German dataset for this study. First, we reproduce the multi-document summaries for English language by following one of the recent studies. Next, we show the applicability of the model to German language by achieving state-of-the-art performance on German MDS. We perform an in-depth error analysis of the followed approach for both languages, which leads us to identifying most notable errors, from made-up facts and topic delimitation, and quantifying the amount of extractiveness.</abstract>
<identifier type="citekey">johner-etal-2021-error</identifier>
<location>
<url>https://aclanthology.org/2021.nodalida-main.43/</url>
</location>
<part>
<date>2021-may 31–2 jun</date>
<extent unit="page">
<start>391</start>
<end>397</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Error Analysis of using BART for Multi-Document Summarization: A Study for English and German Language
%A Johner, Timo
%A Jana, Abhik
%A Biemann, Chris
%Y Dobnik, Simon
%Y Øvrelid, Lilja
%S Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)
%D 2021
%8 may 31–2 jun
%I Linköping University Electronic Press, Sweden
%C Reykjavik, Iceland (Online)
%F johner-etal-2021-error
%X Recent research using pre-trained language models for multi-document summarization task lacks deep investigation of potential erroneous cases and their possible application on other languages. In this work, we apply a pre-trained language model (BART) for multi-document summarization (MDS) task using both fine-tuning and without fine-tuning. We use two English datasets and one German dataset for this study. First, we reproduce the multi-document summaries for English language by following one of the recent studies. Next, we show the applicability of the model to German language by achieving state-of-the-art performance on German MDS. We perform an in-depth error analysis of the followed approach for both languages, which leads us to identifying most notable errors, from made-up facts and topic delimitation, and quantifying the amount of extractiveness.
%U https://aclanthology.org/2021.nodalida-main.43/
%P 391-397
Markdown (Informal)
[Error Analysis of using BART for Multi-Document Summarization: A Study for English and German Language](https://aclanthology.org/2021.nodalida-main.43/) (Johner et al., NoDaLiDa 2021)
ACL