mlsanityData to 7 Oct 2026

Predictive Chemistry Augmented with Text Retrieval

arXiv 2312.04881 ↗First posted 8 Dec 2023cs.CL cs.AI cs.IRcited by 9

Not on the map. Why?

Abstract (arXiv)

This paper focuses on using natural language descriptions to enhance predictive models in the chemistry field. Conventionally, chemoinformatics models are trained with extensive structured data manually extracted from the literature. In this paper, we introduce TextReact, a novel method that directly augments predictive chemistry with texts retrieved from the literature. TextReact retrieves text descriptions relevant for a given chemical reaction, and then aligns them with the molecular representation of the reaction. This alignment is enhanced via an auxiliary masked LM objective incorporated in the predictor training. We empirically validate the framework on two chemistry tasks: reaction condition recommendation and one-step retrosynthesis. By leveraging text retrieval, TextReact significantly outperforms state-of-the-art chemoinformatics models trained solely on molecular data.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 34 of its 62 references that are in the map. First posted on arXiv 8 Dec 2023.

Builds on

34 of 62 references.

References · 34

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  6. 2017Billion-scale similarity search with GPUscited by 2,477
  7. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  8. 2019SciBERT: A Pretrained Language Model for Scientific Textcited by 1,404
  9. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,255
  10. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,026
  11. 2019SpanBERT: Improving Pre-training by Representing and Predicting Spanscited by 832
  12. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
22 more
  1. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
  2. 2019End-to-End Learning of Visual Representations from Uncurated Instructional Videoscited by 506
  3. 2019Analyzing Learned Molecular Representations for Property Predictioncited by 373
  4. 2020ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Predictioncited by 332
  5. 2017Learning to Plan Chemical Synthesescited by 175
  6. 2020Retrosynthesis Prediction with Conditional Graph Logic Networkcited by 103
  7. 2014Deep Fragment Embeddings for Bidirectional Image Sentence Mappingcited by 99
  8. 2020A Graph to Graphs Framework for Retrosynthesis Predictioncited by 85
  9. 2017Retrosynthetic reaction prediction using neural sequence-to-sequence modelscited by 82
  10. 2017Learning with Latent Languagecited by 75
  11. 2015Language Understanding for Text-based Games Using Deep Reinforcement Learningcited by 70
  12. 2020Learning Graph Models for Retrosynthesis Predictioncited by 64
  13. 2017Fine-graind Image Classification via Combining Vision and Languagecited by 51
  14. 2019Environmental drivers of systematicity and generalization in a situated agentcited by 50
  15. 2022MolScribe: Robust Molecular Structure Recognition with Image-To-Graph Generationcited by 48
  16. 2022Tevatron: An Efficient and Flexible Toolkit for Dense Retrievalcited by 47
  17. 2020ALICE: Active Learning with Contrastive Natural Language Explanationscited by 36
  18. 2017See, Hear, and Read: Deep Aligned Representationscited by 32
  19. 2019Shaping Visual Representations with Language for Few-shot Classificationcited by 27
  20. 2023RxnScribe: A Sequence Generation Model for Reaction Diagram Parsingcited by 16
  21. 2019Improving Chemical Named Entity Recognition in Patents with Contextualized Word Embeddingscited by 9
  22. 2020Graph Neural Networks for the Prediction of Substrate-Specific Organic Reaction Conditionscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 2; 2026: 1.

9 papers.

  1. 2024Leveraging Biomolecule and Natural Language through Multi-Modal Learning: A Surveycited by 16
  2. 2024OpenChemIE: An Information Extraction Toolkit For Chemistry Literaturecited by 16
  3. 2024PRESTO: Progressive Pretraining Enhances Synthetic Chemistry Outcomescited by 14
  4. 2024Preference Optimization for Molecule Synthesis with Conditional Residual Energy-based Modelscited by 6
  5. 2024Bridging Text and Molecule: A Survey on Multimodal Frameworks for Moleculecited by 4
  6. 2026Agentic reinforcement learning empowers next-generation chemical language models for molecular design and synthesiscited by 4
  7. 2024Text-Augmented Multimodal LLMs for Chemical Reaction Condition Recommendationcited by 1
  8. 2025RAISE: Enhancing Scientific Reasoning in LLMs via Step-by-Step Retrievalcited by 1
  9. 2025AssayMatch: Learning to Select Data for Molecular Activity Modelscited by 1