{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/translation-between-molecules-and-natural","title":"Translation between Molecules and Natural Language","arxiv_id":"2204.11817","date":"2022-04-25","proceeding":null,"authors":["Carl Edwards","Tuan Lai","Kevin Ros","Garrett Honke","Kyunghyun Cho","Heng Ji"],"abstract":"We present $\\textbf{MolT5}$ $-$ a self-supervised learning framework for pretraining models on a vast amount of unlabeled natural language text and molecule strings. $\\textbf{MolT5}$ allows for new, useful, and challenging analogs of traditional vision-language tasks, such as molecule captioning and text-based de novo molecule generation (altogether: translation between molecules and language), which we explore for the first time. Since $\\textbf{MolT5}$ pretrains models on single-modal data, it helps overcome the chemistry domain shortcoming of data scarcity. Furthermore, we consider several metrics, including a new cross-modal embedding-based metric, to evaluate the tasks of molecule captioning and text-based molecule generation. Our results show that $\\textbf{MolT5}$-based models are able to generate outputs, both molecules and captions, which in many cases are high quality.","url_abs":"https://arxiv.org/abs/2204.11817v3","url_pdf":"https://arxiv.org/pdf/2204.11817v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"translation-between-molecules-and-natural","repo_url":"https://github.com/blender-nlp/MolT5","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"drug-discovery","task_name":"Drug Discovery"},{"task_slug":"molecule-captioning","task_name":"Molecule Captioning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"text-based-de-novo-molecule-generation","task_name":"Text-based de novo Molecule Generation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/molecule-captioning-on-chebi-20","task":"Molecule Captioning","dataset":"ChEBI-20","model":"MolT5-Large","rank_in_archive_order":15,"of":33,"metrics":{"BLEU-2":"59.4","BLEU-4":"50.8","METEOR":"61.4","ROUGE-1":"65.4","ROUGE-2":"51.0","ROUGE-L":"59.4","Text2Mol":"58.2"},"uses_additional_data":false},{"leaderboard":"/sota/molecule-captioning-on-chebi-20","task":"Molecule Captioning","dataset":"ChEBI-20","model":"MolT5-Base","rank_in_archive_order":28,"of":33,"metrics":{"BLEU-2":"54.0","BLEU-4":"45.7","METEOR":"56.9","ROUGE-1":"63.4","ROUGE-2":"48.5","ROUGE-L":"57.8","Text2Mol":"54.7"},"uses_additional_data":false},{"leaderboard":"/sota/molecule-captioning-on-chebi-20","task":"Molecule Captioning","dataset":"ChEBI-20","model":"MolT5-Small","rank_in_archive_order":31,"of":33,"metrics":{"BLEU-2":"51.9","BLEU-4":"43.6","METEOR":"55.1","ROUGE-1":"62.0","ROUGE-2":"46.9","ROUGE-L":"56.3","Text2Mol":"54.0"},"uses_additional_data":false},{"leaderboard":"/sota/molecule-captioning-on-l-m-24","task":"Molecule Captioning","dataset":"L+M-24","model":"MolT5-Large","rank_in_archive_order":3,"of":6,"metrics":{"BLEU-2":"76.9","BLEU-4":"55.6","METEOR":"74.3","ROUGE-1":"77.7","ROUGE-2":"58.0","ROUGE-L":"55.7"},"uses_additional_data":false},{"leaderboard":"/sota/molecule-captioning-on-l-m-24","task":"Molecule Captioning","dataset":"L+M-24","model":"MolT5-Base","rank_in_archive_order":5,"of":6,"metrics":{"BLEU-2":"73.8","BLEU-4":"53.5","METEOR":"71.8","ROUGE-1":"75.0","ROUGE-2":"55.9","ROUGE-L":"53.9"},"uses_additional_data":false},{"leaderboard":"/sota/molecule-captioning-on-l-m-24","task":"Molecule Captioning","dataset":"L+M-24","model":"MolT5-Small","rank_in_archive_order":6,"of":6,"metrics":{"BLEU-2":"70.9","BLEU-4":"51.2","METEOR":"70.1","ROUGE-1":"74.5","ROUGE-2":"55.8","ROUGE-L":"54.4"},"uses_additional_data":false},{"leaderboard":"/sota/text-based-de-novo-molecule-generation-on","task":"Text-based de novo Molecule Generation","dataset":"ChEBI-20","model":"MolT5-Large","rank_in_archive_order":6,"of":20,"metrics":{"BLEU":"85.4","Exact Match":"30.2","Frechet ChemNet Distance (FCD)":"1.20","Levenshtein":"16.07","MACCS FTS":"83.4","Morgan FTS":"68.4","Parameter Count":"770000000","RDK FTS":"74.6","Text2Mol":"55.4","Validity":"90.5"},"uses_additional_data":false},{"leaderboard":"/sota/text-based-de-novo-molecule-generation-on","task":"Text-based de novo Molecule Generation","dataset":"ChEBI-20","model":"MolT5-Large-HV","rank_in_archive_order":12,"of":20,"metrics":{"BLEU":"81.0","Exact Match":"31.4","Frechet ChemNet Distance (FCD)":"0.44","Levenshtein":"16.758","MACCS FTS":"87.2","Morgan FTS":"72.2","Parameter Count":"770000000","RDK FTS":"78.6","Text2Mol":"59.0","Validity":"99.6"},"uses_additional_data":false},{"leaderboard":"/sota/text-based-de-novo-molecule-generation-on","task":"Text-based de novo Molecule Generation","dataset":"ChEBI-20","model":"MolT5-base","rank_in_archive_order":15,"of":20,"metrics":{"BLEU":"76.9","Exact Match":"8.1","Frechet ChemNet Distance (FCD)":"2.18","Levenshtein":"24.458","MACCS FTS":"72.1","Morgan FTS":"52.9","Parameter Count":"220000000","RDK FTS":"58.8","Text2Mol":"49.6","Validity":"77.2"},"uses_additional_data":false},{"leaderboard":"/sota/text-based-de-novo-molecule-generation-on","task":"Text-based de novo Molecule Generation","dataset":"ChEBI-20","model":"MolT5-small","rank_in_archive_order":17,"of":20,"metrics":{"BLEU":"75.5","Exact Match":"7.9","Frechet ChemNet Distance (FCD)":"2.49","Levenshtein":"25.988","MACCS FTS":"70.3","Morgan FTS":"51.7","Parameter Count":"60000000","RDK FTS":"56.8","Text2Mol":"48.2","Validity":"72.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.11817","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.11817"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/blender-nlp/MolT5","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/blendernlp/MolT5","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"c4e38096a64d0bfa","entry":"build_smiles_vocab","repo":"blender-nlp/MolT5","repo_kind":"official","path":"baselines/main_RNN_caption2smiles.py","file_url":"https://github.com/blender-nlp/MolT5/blob/HEAD/baselines/main_RNN_caption2smiles.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"c4e38096a64d0bfa"}},{"code_sha256_prefix":"5567d53edbc7d0d2","entry":"build_smiles_vocab","repo":"blender-nlp/MolT5","repo_kind":"official","path":"baselines/main_transformer_caption2smiles.py","file_url":"https://github.com/blender-nlp/MolT5/blob/HEAD/baselines/main_transformer_caption2smiles.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"5567d53edbc7d0d2"}},{"code_sha256_prefix":"c8ed36180a390809","entry":"create_mask","repo":"blender-nlp/MolT5","repo_kind":"official","path":"baselines/main_transformer_caption2smiles.py","file_url":"https://github.com/blender-nlp/MolT5/blob/HEAD/baselines/main_transformer_caption2smiles.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"c8ed36180a390809"}},{"code_sha256_prefix":"5da85d40a7a21ba4","entry":"generate_square_subsequent_mask","repo":"blender-nlp/MolT5","repo_kind":"official","path":"baselines/main_transformer_caption2smiles.py","file_url":"https://github.com/blender-nlp/MolT5/blob/HEAD/baselines/main_transformer_caption2smiles.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"5da85d40a7a21ba4"}},{"code_sha256_prefix":"25307394e75462fd","entry":"maskNLLLoss","repo":"blender-nlp/MolT5","repo_kind":"official","path":"baselines/main_RNN_caption2smiles.py","file_url":"https://github.com/blender-nlp/MolT5/blob/HEAD/baselines/main_RNN_caption2smiles.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"25307394e75462fd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}