@inproceedings{ganeeva-etal-2024-lost,
title = "Lost in Translation: Chemical Language Models and the Misunderstanding of Molecule Structures",
author = "Ganeeva, Veronika and
Sakhovskiy, Andrey and
Khrabrov, Kuzma and
Savchenko, Andrey and
Kadurin, Artur and
Tutubalina, Elena",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.760",
pages = "12994--13013",
abstract = "The recent integration of chemistry with natural language processing (NLP) has advanced drug discovery. Molecule representation in language models (LMs) is crucial in enhancing chemical understanding. We propose Augmented Molecular Retrieval (AMORE), a flexible zero-shot framework for assessment of Chemistry LMs of different natures: trained solely on molecules for chemical tasks and on a combined corpus of natural language texts and string-based structures. The framework relies on molecule augmentations that preserve an underlying chemical, such as kekulization and cycle replacements. We evaluate encoder-only and generative LMs by calculating a metric based on the similarity score between distributed representations of molecules and their augmentations. Our experiments on ChEBI-20 and QM9 benchmarks show that these models exhibit significantly lower scores than graph-based molecular models trained without language modeling objectives. Additionally, our results on the molecule captioning task for cross-domain models, MolT5 and Text+Chem T5, demonstrate that the lower the representation-based evaluation metrics, the lower the classical text generation metrics like ROUGE and METEOR.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ganeeva-etal-2024-lost">
<titleInfo>
<title>Lost in Translation: Chemical Language Models and the Misunderstanding of Molecule Structures</title>
</titleInfo>
<name type="personal">
<namePart type="given">Veronika</namePart>
<namePart type="family">Ganeeva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrey</namePart>
<namePart type="family">Sakhovskiy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kuzma</namePart>
<namePart type="family">Khrabrov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrey</namePart>
<namePart type="family">Savchenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artur</namePart>
<namePart type="family">Kadurin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Tutubalina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The recent integration of chemistry with natural language processing (NLP) has advanced drug discovery. Molecule representation in language models (LMs) is crucial in enhancing chemical understanding. We propose Augmented Molecular Retrieval (AMORE), a flexible zero-shot framework for assessment of Chemistry LMs of different natures: trained solely on molecules for chemical tasks and on a combined corpus of natural language texts and string-based structures. The framework relies on molecule augmentations that preserve an underlying chemical, such as kekulization and cycle replacements. We evaluate encoder-only and generative LMs by calculating a metric based on the similarity score between distributed representations of molecules and their augmentations. Our experiments on ChEBI-20 and QM9 benchmarks show that these models exhibit significantly lower scores than graph-based molecular models trained without language modeling objectives. Additionally, our results on the molecule captioning task for cross-domain models, MolT5 and Text+Chem T5, demonstrate that the lower the representation-based evaluation metrics, the lower the classical text generation metrics like ROUGE and METEOR.</abstract>
<identifier type="citekey">ganeeva-etal-2024-lost</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.760</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>12994</start>
<end>13013</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lost in Translation: Chemical Language Models and the Misunderstanding of Molecule Structures
%A Ganeeva, Veronika
%A Sakhovskiy, Andrey
%A Khrabrov, Kuzma
%A Savchenko, Andrey
%A Kadurin, Artur
%A Tutubalina, Elena
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F ganeeva-etal-2024-lost
%X The recent integration of chemistry with natural language processing (NLP) has advanced drug discovery. Molecule representation in language models (LMs) is crucial in enhancing chemical understanding. We propose Augmented Molecular Retrieval (AMORE), a flexible zero-shot framework for assessment of Chemistry LMs of different natures: trained solely on molecules for chemical tasks and on a combined corpus of natural language texts and string-based structures. The framework relies on molecule augmentations that preserve an underlying chemical, such as kekulization and cycle replacements. We evaluate encoder-only and generative LMs by calculating a metric based on the similarity score between distributed representations of molecules and their augmentations. Our experiments on ChEBI-20 and QM9 benchmarks show that these models exhibit significantly lower scores than graph-based molecular models trained without language modeling objectives. Additionally, our results on the molecule captioning task for cross-domain models, MolT5 and Text+Chem T5, demonstrate that the lower the representation-based evaluation metrics, the lower the classical text generation metrics like ROUGE and METEOR.
%U https://aclanthology.org/2024.findings-emnlp.760
%P 12994-13013
Markdown (Informal)
[Lost in Translation: Chemical Language Models and the Misunderstanding of Molecule Structures](https://aclanthology.org/2024.findings-emnlp.760) (Ganeeva et al., Findings 2024)
ACL