{"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/learning-semantic-textual-similarity-from","title":"Learning Semantic Textual Similarity from Conversations","arxiv_id":"1804.07754","date":"2018-04-20","proceeding":"WS 2018 7","authors":["Yinfei Yang","Steve Yuan","Daniel Cer","Sheng-yi Kong","Noah Constant","Petr Pilar","Heming Ge","Yun-Hsuan Sung","Brian Strope","Ray Kurzweil"],"abstract":"We present a novel approach to learn representations for sentence-level\nsemantic similarity using conversational data. Our method trains an\nunsupervised model to predict conversational input-response pairs. The\nresulting sentence embeddings perform well on the semantic textual similarity\n(STS) benchmark and SemEval 2017's Community Question Answering (CQA) question\nsimilarity subtask. Performance is further improved by introducing multitask\ntraining combining the conversational input-response prediction task and a\nnatural language inference task. Extensive experiments show the proposed model\nachieves the best performance among all neural models on the STS benchmark and\nis competitive with the state-of-the-art feature engineered and mixed systems\nin both tasks.","url_abs":"http://arxiv.org/abs/1804.07754v1","url_pdf":"http://arxiv.org/pdf/1804.07754v1.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":"learning-semantic-textual-similarity-from","repo_url":"https://github.com/nickyeolk/info_retrieve","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"community-question-answering","task_name":"Community Question Answering"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"question-similarity","task_name":"Question Similarity"},{"task_slug":"sts","task_name":"STS"},{"task_slug":"sts-benchmark","task_name":"STS Benchmark"},{"task_slug":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-embeddings","task_name":"Sentence Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.07754","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.07754"}},"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/nickyeolk/info_retrieve","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":17},"by_repo_kind":{"listed":{"samples":17,"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":"fc35b5b7943a910b","entry":"add_period","repo":"nickyeolk/info_retrieve","repo_kind":"listed","path":"src/importance.py","file_url":"https://github.com/nickyeolk/info_retrieve/blob/HEAD/src/importance.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fc35b5b7943a910b"}},{"code_sha256_prefix":"6fc5d2d5b1f9523e","entry":"add_period_html","repo":"nickyeolk/info_retrieve","repo_kind":"listed","path":"src/importance.py","file_url":"https://github.com/nickyeolk/info_retrieve/blob/HEAD/src/importance.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6fc5d2d5b1f9523e"}},{"code_sha256_prefix":"6d48135dd9946bb4","entry":"clean_txt","repo":"nickyeolk/info_retrieve","repo_kind":"listed","path":"src/utils.py","file_url":"https://github.com/nickyeolk/info_retrieve/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6d48135dd9946bb4"}},{"code_sha256_prefix":"a81e3c623f9e5618","entry":"extract","repo":"nickyeolk/info_retrieve","repo_kind":"listed","path":"app_flask.py","file_url":"https://github.com/nickyeolk/info_retrieve/blob/HEAD/app_flask.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a81e3c623f9e5618"}},{"code_sha256_prefix":"d4c5fb19a0477c97","entry":"format_func","repo":"nickyeolk/info_retrieve","repo_kind":"listed","path":"st_demo.py","file_url":"https://github.com/nickyeolk/info_retrieve/blob/HEAD/st_demo.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d4c5fb19a0477c97"}},{"code_sha256_prefix":"cd246cb6c6617d87","entry":"generate_mappings","repo":"nickyeolk/info_retrieve","repo_kind":"listed","path":"src/kb_handler.py","file_url":"https://github.com/nickyeolk/info_retrieve/blob/HEAD/src/kb_handler.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cd246cb6c6617d87"}},{"code_sha256_prefix":"6b4945d2e09fe154","entry":"get_ids","repo":"nickyeolk/info_retrieve","repo_kind":"listed","path":"src/bert_tokenization.py","file_url":"https://github.com/nickyeolk/info_retrieve/blob/HEAD/src/bert_tokenization.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6b4945d2e09fe154"}},{"code_sha256_prefix":"fe26978879cca681","entry":"get_masks","repo":"nickyeolk/info_retrieve","repo_kind":"listed","path":"src/bert_tokenization.py","file_url":"https://github.com/nickyeolk/info_retrieve/blob/HEAD/src/bert_tokenization.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fe26978879cca681"}},{"code_sha256_prefix":"922a8461783d514b","entry":"get_segments","repo":"nickyeolk/info_retrieve","repo_kind":"listed","path":"src/bert_tokenization.py","file_url":"https://github.com/nickyeolk/info_retrieve/blob/HEAD/src/bert_tokenization.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"922a8461783d514b"}},{"code_sha256_prefix":"143be1a6554ab483","entry":"hard_triplet_generator","repo":"nickyeolk/info_retrieve","repo_kind":"listed","path":"src/finetune_eval.py","file_url":"https://github.com/nickyeolk/info_retrieve/blob/HEAD/src/finetune_eval.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"143be1a6554ab483"}},{"code_sha256_prefix":"7c606cc27a65fdbb","entry":"mrr","repo":"nickyeolk/info_retrieve","repo_kind":"listed","path":"src/finetune_eval.py","file_url":"https://github.com/nickyeolk/info_retrieve/blob/HEAD/src/finetune_eval.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7c606cc27a65fdbb"}},{"code_sha256_prefix":"7041cf85b5729cb5","entry":"parse_string","repo":"nickyeolk/info_retrieve","repo_kind":"listed","path":"src/importance.py","file_url":"https://github.com/nickyeolk/info_retrieve/blob/HEAD/src/importance.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7041cf85b5729cb5"}},{"code_sha256_prefix":"c8a48beb0be3672c","entry":"question_cleaner","repo":"nickyeolk/info_retrieve","repo_kind":"listed","path":"src/utils.py","file_url":"https://github.com/nickyeolk/info_retrieve/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c8a48beb0be3672c"}},{"code_sha256_prefix":"d1ccb61839e8ab51","entry":"random_triplet_generator","repo":"nickyeolk/info_retrieve","repo_kind":"listed","path":"src/finetune_eval.py","file_url":"https://github.com/nickyeolk/info_retrieve/blob/HEAD/src/finetune_eval.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d1ccb61839e8ab51"}},{"code_sha256_prefix":"9aff0e1769d7891e","entry":"read_txt","repo":"nickyeolk/info_retrieve","repo_kind":"listed","path":"src/utils.py","file_url":"https://github.com/nickyeolk/info_retrieve/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9aff0e1769d7891e"}},{"code_sha256_prefix":"370a6e91bad59927","entry":"triplet_loss","repo":"nickyeolk/info_retrieve","repo_kind":"listed","path":"src/metric_learning.py","file_url":"https://github.com/nickyeolk/info_retrieve/blob/HEAD/src/metric_learning.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"370a6e91bad59927"}},{"code_sha256_prefix":"68b251e42b81afcd","entry":"unique_indexing","repo":"nickyeolk/info_retrieve","repo_kind":"listed","path":"src/kb_handler.py","file_url":"https://github.com/nickyeolk/info_retrieve/blob/HEAD/src/kb_handler.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"68b251e42b81afcd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}