{"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/toward-interpretable-semantic-textual","title":"Toward Interpretable Semantic Textual Similarity via Optimal Transport-based Contrastive Sentence Learning","arxiv_id":"2202.13196","date":"2022-02-26","proceeding":"ACL 2022 5","authors":["Seonghyeon Lee","Dongha Lee","Seongbo Jang","Hwanjo Yu"],"abstract":"Recently, finetuning a pretrained language model to capture the similarity between sentence embeddings has shown the state-of-the-art performance on the semantic textual similarity (STS) task. However, the absence of an interpretation method for the sentence similarity makes it difficult to explain the model output. In this work, we explicitly describe the sentence distance as the weighted sum of contextualized token distances on the basis of a transportation problem, and then present the optimal transport-based distance measure, named RCMD; it identifies and leverages semantically-aligned token pairs. In the end, we propose CLRCMD, a contrastive learning framework that optimizes RCMD of sentence pairs, which enhances the quality of sentence similarity and their interpretation. Extensive experiments demonstrate that our learning framework outperforms other baselines on both STS and interpretable-STS benchmarks, indicating that it computes effective sentence similarity and also provides interpretation consistent with human judgement. The code and checkpoint are publicly available at https://github.com/sh0416/clrcmd.","url_abs":"https://arxiv.org/abs/2202.13196v2","url_pdf":"https://arxiv.org/pdf/2202.13196v2.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":"toward-interpretable-semantic-textual","repo_url":"https://github.com/sh0416/clrcmd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"sts","task_name":"STS"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-embeddings","task_name":"Sentence Embeddings"},{"task_slug":"sentence-similarity","task_name":"Sentence Similarity"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2202.13196","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.13196"}},"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":"deterministic:regex_extraction","url":"https://github.com/sh0416/clrcmd","reach":null}],"summary":{"ran":1,"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"04a62d4701f99cb5","entry":"RelaxedWordMoverSimilarity","repo":"sh0416/clrcmd","repo_kind":"official","path":"src/clrcmd/models.py","file_url":"https://github.com/sh0416/clrcmd/blob/HEAD/src/clrcmd/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"04a62d4701f99cb5"}},{"code_sha256_prefix":"64dbc58af5081065","entry":"masked_mean","repo":"sh0416/clrcmd","repo_kind":"official","path":"src/clrcmd/models.py","file_url":"https://github.com/sh0416/clrcmd/blob/HEAD/src/clrcmd/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"64dbc58af5081065"}},{"code_sha256_prefix":"09bf1daaa67faf33","entry":"masked_sum","repo":"sh0416/clrcmd","repo_kind":"official","path":"src/clrcmd/models.py","file_url":"https://github.com/sh0416/clrcmd/blob/HEAD/src/clrcmd/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"09bf1daaa67faf33"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}