@inproceedings{tran-etal-2024-mol2lang,
title = "{M}ol2{L}ang-{VLM}: Vision- and Text-Guided Generative Pre-trained Language Models for Advancing Molecule Captioning through Multimodal Fusion",
author = "Tran, Duong and
Pham, Nhat Truong and
Nguyen, Nguyen and
Manavalan, Balachandran",
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-1.12",
pages = "97--102",
abstract = "This paper introduces Mol2Lang-VLM, an enhanced method for refining generative pre-trained language models for molecule captioning using multimodal features to achieve more accurate caption generation. Our approach leverages the encoder and decoder blocks of the Transformer-based architecture by introducing third sub-layers into both. Specifically, we insert sub-layers in the encoder to fuse features from SELFIES strings and molecular images, while the decoder fuses features from SMILES strings and their corresponding descriptions. Moreover, cross multi-head attention is employed instead of common multi-head attention to enable the decoder to attend to the encoder{'}s output, thereby integrating the encoded contextual information for better and more accurate caption generation. Performance evaluation on the CheBI-20 and L+M-24 benchmark datasets demonstrates Mol2Lang-VLM{'}s superiority, achieving higher accuracy and quality in caption generation compared to existing methods. Our code and pre-processed data are available at https://github.com/nhattruongpham/mol-lang-bridge/tree/mol2lang/.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tran-etal-2024-mol2lang">
<titleInfo>
<title>Mol2Lang-VLM: Vision- and Text-Guided Generative Pre-trained Language Models for Advancing Molecule Captioning through Multimodal Fusion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Duong</namePart>
<namePart type="family">Tran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nhat</namePart>
<namePart type="given">Truong</namePart>
<namePart type="family">Pham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nguyen</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Balachandran</namePart>
<namePart type="family">Manavalan</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 introduces Mol2Lang-VLM, an enhanced method for refining generative pre-trained language models for molecule captioning using multimodal features to achieve more accurate caption generation. Our approach leverages the encoder and decoder blocks of the Transformer-based architecture by introducing third sub-layers into both. Specifically, we insert sub-layers in the encoder to fuse features from SELFIES strings and molecular images, while the decoder fuses features from SMILES strings and their corresponding descriptions. Moreover, cross multi-head attention is employed instead of common multi-head attention to enable the decoder to attend to the encoder’s output, thereby integrating the encoded contextual information for better and more accurate caption generation. Performance evaluation on the CheBI-20 and L+M-24 benchmark datasets demonstrates Mol2Lang-VLM’s superiority, achieving higher accuracy and quality in caption generation compared to existing methods. Our code and pre-processed data are available at https://github.com/nhattruongpham/mol-lang-bridge/tree/mol2lang/.</abstract>
<identifier type="citekey">tran-etal-2024-mol2lang</identifier>
<location>
<url>https://aclanthology.org/2024.langmol-1.12</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>97</start>
<end>102</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mol2Lang-VLM: Vision- and Text-Guided Generative Pre-trained Language Models for Advancing Molecule Captioning through Multimodal Fusion
%A Tran, Duong
%A Pham, Nhat Truong
%A Nguyen, Nguyen
%A Manavalan, Balachandran
%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 tran-etal-2024-mol2lang
%X This paper introduces Mol2Lang-VLM, an enhanced method for refining generative pre-trained language models for molecule captioning using multimodal features to achieve more accurate caption generation. Our approach leverages the encoder and decoder blocks of the Transformer-based architecture by introducing third sub-layers into both. Specifically, we insert sub-layers in the encoder to fuse features from SELFIES strings and molecular images, while the decoder fuses features from SMILES strings and their corresponding descriptions. Moreover, cross multi-head attention is employed instead of common multi-head attention to enable the decoder to attend to the encoder’s output, thereby integrating the encoded contextual information for better and more accurate caption generation. Performance evaluation on the CheBI-20 and L+M-24 benchmark datasets demonstrates Mol2Lang-VLM’s superiority, achieving higher accuracy and quality in caption generation compared to existing methods. Our code and pre-processed data are available at https://github.com/nhattruongpham/mol-lang-bridge/tree/mol2lang/.
%U https://aclanthology.org/2024.langmol-1.12
%P 97-102
Markdown (Informal)
[Mol2Lang-VLM: Vision- and Text-Guided Generative Pre-trained Language Models for Advancing Molecule Captioning through Multimodal Fusion](https://aclanthology.org/2024.langmol-1.12) (Tran et al., LangMol-WS 2024)
ACL