@inproceedings{reddy-etal-2023-iitr,
title = "{IITR} at {B}io{L}ay{S}umm Task 1:Lay Summarization of {B}io{M}edical articles using Transformers",
author = "Reddy, Venkat praneeth and
Reddy, Pinnapu Reddy Harshavardhan and
Sumedh, Karanam Sai and
Sharma, Raksha",
editor = "Demner-fushman, Dina and
Ananiadou, Sophia and
Cohen, Kevin",
booktitle = "The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.bionlp-1.67",
doi = "10.18653/v1/2023.bionlp-1.67",
pages = "625--628",
abstract = "Initially, we analyzed the datasets in a statistical way so as to learn about various sections{'} contributions to the final summary in both the pros and life datasets. We found that both the datasets have an Introduction and Abstract along with some initial parts of the results contributing to the summary. We considered only these sections in the next stage of analysis. We found the optimal length or no of sentences of each of the Introduction, abstract, and result which contributes best to the summary. After this statistical analysis, we took the pre-trained model Facebook/bart-base and fine-tuned it with both the datasets PLOS and eLife. While fine-tuning and testing the results we have used chunking because the text lengths are huge. So to not lose information due to the number of token constraints of the model, we used chunking. Finally, we saw the eLife model giving more accurate results than PLOS in terms of readability aspect, probably because the PLOS summary is closer to its abstract, we have considered the eLife model as our final model and tuned the hyperparameters. We are ranked 7th overall and 1st in readability",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="reddy-etal-2023-iitr">
<titleInfo>
<title>IITR at BioLaySumm Task 1:Lay Summarization of BioMedical articles using Transformers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Venkat</namePart>
<namePart type="given">praneeth</namePart>
<namePart type="family">Reddy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pinnapu</namePart>
<namePart type="given">Reddy</namePart>
<namePart type="given">Harshavardhan</namePart>
<namePart type="family">Reddy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karanam</namePart>
<namePart type="given">Sai</namePart>
<namePart type="family">Sumedh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raksha</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Initially, we analyzed the datasets in a statistical way so as to learn about various sections’ contributions to the final summary in both the pros and life datasets. We found that both the datasets have an Introduction and Abstract along with some initial parts of the results contributing to the summary. We considered only these sections in the next stage of analysis. We found the optimal length or no of sentences of each of the Introduction, abstract, and result which contributes best to the summary. After this statistical analysis, we took the pre-trained model Facebook/bart-base and fine-tuned it with both the datasets PLOS and eLife. While fine-tuning and testing the results we have used chunking because the text lengths are huge. So to not lose information due to the number of token constraints of the model, we used chunking. Finally, we saw the eLife model giving more accurate results than PLOS in terms of readability aspect, probably because the PLOS summary is closer to its abstract, we have considered the eLife model as our final model and tuned the hyperparameters. We are ranked 7th overall and 1st in readability</abstract>
<identifier type="citekey">reddy-etal-2023-iitr</identifier>
<identifier type="doi">10.18653/v1/2023.bionlp-1.67</identifier>
<location>
<url>https://aclanthology.org/2023.bionlp-1.67</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>625</start>
<end>628</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IITR at BioLaySumm Task 1:Lay Summarization of BioMedical articles using Transformers
%A Reddy, Venkat praneeth
%A Reddy, Pinnapu Reddy Harshavardhan
%A Sumedh, Karanam Sai
%A Sharma, Raksha
%Y Demner-fushman, Dina
%Y Ananiadou, Sophia
%Y Cohen, Kevin
%S The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F reddy-etal-2023-iitr
%X Initially, we analyzed the datasets in a statistical way so as to learn about various sections’ contributions to the final summary in both the pros and life datasets. We found that both the datasets have an Introduction and Abstract along with some initial parts of the results contributing to the summary. We considered only these sections in the next stage of analysis. We found the optimal length or no of sentences of each of the Introduction, abstract, and result which contributes best to the summary. After this statistical analysis, we took the pre-trained model Facebook/bart-base and fine-tuned it with both the datasets PLOS and eLife. While fine-tuning and testing the results we have used chunking because the text lengths are huge. So to not lose information due to the number of token constraints of the model, we used chunking. Finally, we saw the eLife model giving more accurate results than PLOS in terms of readability aspect, probably because the PLOS summary is closer to its abstract, we have considered the eLife model as our final model and tuned the hyperparameters. We are ranked 7th overall and 1st in readability
%R 10.18653/v1/2023.bionlp-1.67
%U https://aclanthology.org/2023.bionlp-1.67
%U https://doi.org/10.18653/v1/2023.bionlp-1.67
%P 625-628
Markdown (Informal)
[IITR at BioLaySumm Task 1:Lay Summarization of BioMedical articles using Transformers](https://aclanthology.org/2023.bionlp-1.67) (Reddy et al., BioNLP 2023)
ACL