@inproceedings{tanaka-etal-2024-nlpeople,
title = "{NLP}eople at \textit{ {L}+{M}-24} Shared Task: An Ensembled Approach for Molecule Captioning from {SMILES}",
author = "Tanaka, Shinnosuke and
Mak, Carol and
Cipcigan, Flaviu and
Barry, James and
Elkaref, Mohab and
Moses, Movina and
Kuruvanthodi, Vishnudev and
Mel, Geeth",
editor = "Edwards, Carl and
Wang, Qingyun and
Li, Manling and
Zhao, Lawrence and
Hope, Tom and
Ji, Heng",
booktitle = "Proceedings of the 1st Workshop on Language + Molecules (L+M 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.langmol-1.10",
pages = "85--90",
abstract = "This paper presents our approach submitted to the Language + Molecules 2024 (\textit{L+M-24}) Shared Task in the Molecular Captioning track. The task involves generating captions that describe the properties of molecules that are provided in SMILES format.We propose a method for the task that decomposes the challenge of generating captions from SMILES into a classification problem,where we first predict the molecule{'}s properties. The molecules whose properties can be predicted with high accuracy show high translation metric scores in the caption generation by LLMs, while others produce low scores. Then we use the predicted properties to select the captions generated by different types of LLMs, and use that prediction as the final output. Our submission achieved an overall increase score of 15.21 on the dev set and 12.30 on the evaluation set, based on translation metrics and property metrics from the baseline.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tanaka-etal-2024-nlpeople">
<titleInfo>
<title>NLPeople at L+M-24 Shared Task: An Ensembled Approach for Molecule Captioning from SMILES</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shinnosuke</namePart>
<namePart type="family">Tanaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carol</namePart>
<namePart type="family">Mak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flaviu</namePart>
<namePart type="family">Cipcigan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Barry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohab</namePart>
<namePart type="family">Elkaref</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Movina</namePart>
<namePart type="family">Moses</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vishnudev</namePart>
<namePart type="family">Kuruvanthodi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Geeth</namePart>
<namePart type="family">Mel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Language + Molecules (L+M 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carl</namePart>
<namePart type="family">Edwards</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingyun</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manling</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lawrence</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Hope</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents our approach submitted to the Language + Molecules 2024 (L+M-24) Shared Task in the Molecular Captioning track. The task involves generating captions that describe the properties of molecules that are provided in SMILES format.We propose a method for the task that decomposes the challenge of generating captions from SMILES into a classification problem,where we first predict the molecule’s properties. The molecules whose properties can be predicted with high accuracy show high translation metric scores in the caption generation by LLMs, while others produce low scores. Then we use the predicted properties to select the captions generated by different types of LLMs, and use that prediction as the final output. Our submission achieved an overall increase score of 15.21 on the dev set and 12.30 on the evaluation set, based on translation metrics and property metrics from the baseline.</abstract>
<identifier type="citekey">tanaka-etal-2024-nlpeople</identifier>
<location>
<url>https://aclanthology.org/2024.langmol-1.10</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>85</start>
<end>90</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NLPeople at L+M-24 Shared Task: An Ensembled Approach for Molecule Captioning from SMILES
%A Tanaka, Shinnosuke
%A Mak, Carol
%A Cipcigan, Flaviu
%A Barry, James
%A Elkaref, Mohab
%A Moses, Movina
%A Kuruvanthodi, Vishnudev
%A Mel, Geeth
%Y Edwards, Carl
%Y Wang, Qingyun
%Y Li, Manling
%Y Zhao, Lawrence
%Y Hope, Tom
%Y Ji, Heng
%S Proceedings of the 1st Workshop on Language + Molecules (L+M 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F tanaka-etal-2024-nlpeople
%X This paper presents our approach submitted to the Language + Molecules 2024 (L+M-24) Shared Task in the Molecular Captioning track. The task involves generating captions that describe the properties of molecules that are provided in SMILES format.We propose a method for the task that decomposes the challenge of generating captions from SMILES into a classification problem,where we first predict the molecule’s properties. The molecules whose properties can be predicted with high accuracy show high translation metric scores in the caption generation by LLMs, while others produce low scores. Then we use the predicted properties to select the captions generated by different types of LLMs, and use that prediction as the final output. Our submission achieved an overall increase score of 15.21 on the dev set and 12.30 on the evaluation set, based on translation metrics and property metrics from the baseline.
%U https://aclanthology.org/2024.langmol-1.10
%P 85-90
Markdown (Informal)
[NLPeople at L+M-24 Shared Task: An Ensembled Approach for Molecule Captioning from SMILES](https://aclanthology.org/2024.langmol-1.10) (Tanaka et al., LangMol-WS 2024)
ACL
- Shinnosuke Tanaka, Carol Mak, Flaviu Cipcigan, James Barry, Mohab Elkaref, Movina Moses, Vishnudev Kuruvanthodi, and Geeth Mel. 2024. NLPeople at L+M-24 Shared Task: An Ensembled Approach for Molecule Captioning from SMILES. In Proceedings of the 1st Workshop on Language + Molecules (L+M 2024), pages 85–90, Bangkok, Thailand. Association for Computational Linguistics.