{"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/joint-learning-of-sentence-embeddings-for","title":"Joint Learning of Sentence Embeddings for Relevance and Entailment","arxiv_id":"1605.04655","date":"2016-05-16","proceeding":"WS 2016 8","authors":["Petr Baudis","Silvestr Stanko","Jan Sedivy"],"abstract":"We consider the problem of Recognizing Textual Entailment within an\nInformation Retrieval context, where we must simultaneously determine the\nrelevancy as well as degree of entailment for individual pieces of evidence to\ndetermine a yes/no answer to a binary natural language question.\n  We compare several variants of neural networks for sentence embeddings in a\nsetting of decision-making based on evidence of varying relevance. We propose a\nbasic model to integrate evidence for entailment, show that joint training of\nthe sentence embeddings to model relevance and entailment is feasible even with\nno explicit per-evidence supervision, and show the importance of evaluating\nstrong baselines. We also demonstrate the benefit of carrying over text\ncomprehension model trained on an unrelated task for our small datasets.\n  Our research is motivated primarily by a new open dataset we introduce,\nconsisting of binary questions and news-based evidence snippets. We also apply\nthe proposed relevance-entailment model on a similar task of ranking\nmultiple-choice test answers, evaluating it on a preliminary dataset of school\ntest questions as well as the standard MCTest dataset, where we improve the\nneural model state-of-art.","url_abs":"http://arxiv.org/abs/1605.04655v2","url_pdf":"http://arxiv.org/pdf/1605.04655v2.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":"joint-learning-of-sentence-embeddings-for","repo_url":"https://github.com/brmson/dataset-sts","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"multiple-choice","task_name":"Multiple-choice"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-embeddings","task_name":"Sentence Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}