{"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/textit-l-m-24-building-a-dataset-for-language","title":"L+M-24: Building a Dataset for Language + Molecules @ ACL 2024","arxiv_id":"2403.00791","date":"2024-02-22","proceeding":null,"authors":["Carl Edwards","Qingyun Wang","Lawrence Zhao","Heng Ji"],"abstract":"Language-molecule models have emerged as an exciting direction for molecular discovery and understanding. However, training these models is challenging due to the scarcity of molecule-language pair datasets. At this point, datasets have been released which are 1) small and scraped from existing databases, 2) large but noisy and constructed by performing entity linking on the scientific literature, and 3) built by converting property prediction datasets to natural language using templates. In this document, we detail the $\\textit{L+M-24}$ dataset, which has been created for the Language + Molecules Workshop shared task at ACL 2024. In particular, $\\textit{L+M-24}$ is designed to focus on three key benefits of natural language in molecule design: compositionality, functionality, and abstraction.","url_abs":"https://arxiv.org/abs/2403.00791v2","url_pdf":"https://arxiv.org/pdf/2403.00791v2.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":"textit-l-m-24-building-a-dataset-for-language","repo_url":"https://github.com/language-plus-molecules/lpm-24-dataset","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"entity-linking","task_name":"Entity Linking"},{"task_slug":"property-prediction","task_name":"Property Prediction"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[{"slug":"l-m-24","name":"L+M-24","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.00791","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00791"}},"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/language-plus-molecules/lpm-24-dataset","reach":{"status":"ok"}}],"summary":{"ran":5,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":7,"samples":[{"code_sha256_prefix":"7e2f49645b16c9b8","entry":"flatten","repo":"language-plus-molecules/lpm-24-dataset","repo_kind":"official","path":"evaluation/create_heldout_file.py","file_url":"https://github.com/language-plus-molecules/lpm-24-dataset/blob/HEAD/evaluation/create_heldout_file.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7e2f49645b16c9b8"}},{"code_sha256_prefix":"98b645985f996cab","entry":"flatten_float","repo":"language-plus-molecules/lpm-24-dataset","repo_kind":"official","path":"evaluation/text_property_metrics.py","file_url":"https://github.com/language-plus-molecules/lpm-24-dataset/blob/HEAD/evaluation/text_property_metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"98b645985f996cab"}},{"code_sha256_prefix":"31c23d051121b61b","entry":"proc_line","repo":"language-plus-molecules/lpm-24-dataset","repo_kind":"official","path":"final_evaluation/captioning/scorer.py","file_url":"https://github.com/language-plus-molecules/lpm-24-dataset/blob/HEAD/final_evaluation/captioning/scorer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"31c23d051121b61b"}},{"code_sha256_prefix":"276d317054148ab7","entry":"unflatten","repo":"language-plus-molecules/lpm-24-dataset","repo_kind":"official","path":"evaluation/create_heldout_file.py","file_url":"https://github.com/language-plus-molecules/lpm-24-dataset/blob/HEAD/evaluation/create_heldout_file.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"276d317054148ab7"}},{"code_sha256_prefix":"23df915882394648","entry":"zero_division","repo":"language-plus-molecules/lpm-24-dataset","repo_kind":"official","path":"evaluation/create_heldout_file.py","file_url":"https://github.com/language-plus-molecules/lpm-24-dataset/blob/HEAD/evaluation/create_heldout_file.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"23df915882394648"}},{"code_sha256_prefix":"1661dcb7ecdb3b3e","entry":"evaluate","repo":"language-plus-molecules/lpm-24-dataset","repo_kind":"official","path":"evaluation/text_translation_metrics.py","file_url":"https://github.com/language-plus-molecules/lpm-24-dataset/blob/HEAD/evaluation/text_translation_metrics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1661dcb7ecdb3b3e"}},{"code_sha256_prefix":"a332b9c75c492e25","entry":"evaluate","repo":"language-plus-molecules/lpm-24-dataset","repo_kind":"official","path":"final_evaluation/captioning/scorer.py","file_url":"https://github.com/language-plus-molecules/lpm-24-dataset/blob/HEAD/final_evaluation/captioning/scorer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a332b9c75c492e25"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}