{"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/determining-semantic-textual-similarity-using","title":"Determining Semantic Textual Similarity using Natural Deduction Proofs","arxiv_id":"1707.08713","date":"2017-07-27","proceeding":"EMNLP 2017 9","authors":["Hitomi Yanaka","Koji Mineshima","Pascual Martinez-Gomez","Daisuke Bekki"],"abstract":"Determining semantic textual similarity is a core research subject in natural\nlanguage processing. Since vector-based models for sentence representation\noften use shallow information, capturing accurate semantics is difficult. By\ncontrast, logical semantic representations capture deeper levels of sentence\nsemantics, but their symbolic nature does not offer graded notions of textual\nsimilarity. We propose a method for determining semantic textual similarity by\ncombining shallow features with features extracted from natural deduction\nproofs of bidirectional entailment relations between sentence pairs. For the\nnatural deduction proofs, we use ccg2lambda, a higher-order automatic inference\nsystem, which converts Combinatory Categorial Grammar (CCG) derivation trees\ninto semantic representations and conducts natural deduction proofs.\nExperiments show that our system was able to outperform other logic-based\nsystems and that features derived from the proofs are effective for learning\ntextual similarity.","url_abs":"http://arxiv.org/abs/1707.08713v1","url_pdf":"http://arxiv.org/pdf/1707.08713v1.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":"determining-semantic-textual-similarity-using","repo_url":"https://github.com/mynlp/ccg2lambda","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}