{"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/what-makes-sentences-semantically-related-a","title":"What Makes Sentences Semantically Related: A Textual Relatedness Dataset and Empirical Study","arxiv_id":"2110.04845","date":"2021-10-10","proceeding":null,"authors":["Mohamed Abdalla","Krishnapriya Vishnubhotla","Saif M. Mohammad"],"abstract":"The degree of semantic relatedness of two units of language has long been considered fundamental to understanding meaning. Additionally, automatically determining relatedness has many applications such as question answering and summarization. However, prior NLP work has largely focused on semantic similarity, a subset of relatedness, because of a lack of relatedness datasets. In this paper, we introduce a dataset for Semantic Textual Relatedness, STR-2022, that has 5,500 English sentence pairs manually annotated using a comparative annotation framework, resulting in fine-grained scores. We show that human intuition regarding relatedness of sentence pairs is highly reliable, with a repeat annotation correlation of 0.84. We use the dataset to explore questions on what makes sentences semantically related. We also show the utility of STR-2022 for evaluating automatic methods of sentence representation and for various downstream NLP tasks. Our dataset, data statement, and annotation questionnaire can be found at: https://doi.org/10.5281/zenodo.7599667","url_abs":"https://arxiv.org/abs/2110.04845v4","url_pdf":"https://arxiv.org/pdf/2110.04845v4.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":"what-makes-sentences-semantically-related-a","repo_url":"https://github.com/priya22/semantic-textual-relatedness","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"what-makes-sentences-semantically-related-a","repo_url":"https://github.com/binwang28/rse","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[{"slug":"str-2021","name":"STR-2021","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.04845","atlas_url":"https://app.syntology.ai/?focus=2110.04845","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.04845"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/priya22/semantic-textual-relatedness","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/binwang28/rse","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"unverified":1},"by_repo_kind":{"listed":{"samples":4,"ran":3,"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":"683315c7bd2b8f4b","entry":"load_from_json","repo":"binwang28/rse","repo_kind":"listed","path":"rse_src/data_loader.py","file_url":"https://github.com/binwang28/rse/blob/HEAD/rse_src/data_loader.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"683315c7bd2b8f4b"}},{"code_sha256_prefix":"9c14e6f2d0eb838c","entry":"raw_data_loader","repo":"binwang28/rse","repo_kind":"listed","path":"rse_src/data_loader.py","file_url":"https://github.com/binwang28/rse/blob/HEAD/rse_src/data_loader.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9c14e6f2d0eb838c"}},{"code_sha256_prefix":"738311e63cd8d155","entry":"rse_forward","repo":"binwang28/rse","repo_kind":"listed","path":"rse_src/model_utils.py","file_url":"https://github.com/binwang28/rse/blob/HEAD/rse_src/model_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"738311e63cd8d155"}},{"code_sha256_prefix":"b6468f5023fb91cb","entry":"sentemb_forward","repo":"binwang28/rse","repo_kind":"listed","path":"rse_src/model_utils.py","file_url":"https://github.com/binwang28/rse/blob/HEAD/rse_src/model_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b6468f5023fb91cb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}