{"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/end-task-oriented-textual-entailment-via-deep","title":"End-Task Oriented Textual Entailment via Deep Explorations of Inter-Sentence Interactions","arxiv_id":"1804.08813","date":"2018-04-24","proceeding":"ACL 2018 7","authors":["Wenpeng Yin","Hinrich Schütze","Dan Roth"],"abstract":"This work deals with SciTail, a natural entailment challenge derived from a\nmulti-choice question answering problem. The premises and hypotheses in SciTail\nwere generated with no awareness of each other, and did not specifically aim at\nthe entailment task. This makes it more challenging than other entailment data\nsets and more directly useful to the end-task -- question answering. We propose\nDEISTE (deep explorations of inter-sentence interactions for textual\nentailment) for this entailment task. Given word-to-word interactions between\nthe premise-hypothesis pair ($P$, $H$), DEISTE consists of: (i) a\nparameter-dynamic convolution to make important words in $P$ and $H$ play a\ndominant role in learnt representations; and (ii) a position-aware attentive\nconvolution to encode the representation and position information of the\naligned word pairs. Experiments show that DEISTE gets $\\approx$5\\% improvement\nover prior state of the art and that the pretrained DEISTE on SciTail\ngeneralizes well on RTE-5.","url_abs":"http://arxiv.org/abs/1804.08813v3","url_pdf":"http://arxiv.org/pdf/1804.08813v3.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":"end-task-oriented-textual-entailment-via-deep","repo_url":"https://github.com/yinwenpeng/SciTail","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":null,"task_name":"Position"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"rte","task_name":"RTE"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.08813","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}