{"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/refining-raw-sentence-representations-for","title":"Refining Raw Sentence Representations for Textual Entailment Recognition via Attention","arxiv_id":"1707.03103","date":"2017-07-11","proceeding":"WS 2017 9","authors":["Jorge A. Balazs","Edison Marrese-Taylor","Pablo Loyola","Yutaka Matsuo"],"abstract":"In this paper we present the model used by the team Rivercorners for the 2017\nRepEval shared task. First, our model separately encodes a pair of sentences\ninto variable-length representations by using a bidirectional LSTM. Later, it\ncreates fixed-length raw representations by means of simple aggregation\nfunctions, which are then refined using an attention mechanism. Finally it\ncombines the refined representations of both sentences into a single vector to\nbe used for classification. With this model we obtained test accuracies of\n72.057% and 72.055% in the matched and mismatched evaluation tracks\nrespectively, outperforming the LSTM baseline, and obtaining performances\nsimilar to a model that relies on shared information between sentences (ESIM).\nWhen using an ensemble both accuracies increased to 72.247% and 72.827%\nrespectively.","url_abs":"http://arxiv.org/abs/1707.03103v2","url_pdf":"http://arxiv.org/pdf/1707.03103v2.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":"refining-raw-sentence-representations-for","repo_url":"https://github.com/jabalazs/repeval_rivercorners","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}