{"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/shortcut-stacked-sentence-encoders-for-multi","title":"Shortcut-Stacked Sentence Encoders for Multi-Domain Inference","arxiv_id":"1708.02312","date":"2017-08-07","proceeding":"WS 2017 9","authors":["Yixin Nie","Mohit Bansal"],"abstract":"We present a simple sequential sentence encoder for multi-domain natural\nlanguage inference. Our encoder is based on stacked bidirectional LSTM-RNNs\nwith shortcut connections and fine-tuning of word embeddings. The overall\nsupervised model uses the above encoder to encode two input sentences into two\nvectors, and then uses a classifier over the vector combination to label the\nrelationship between these two sentences as that of entailment, contradiction,\nor neural. Our Shortcut-Stacked sentence encoders achieve strong improvements\nover existing encoders on matched and mismatched multi-domain natural language\ninference (top non-ensemble single-model result in the EMNLP RepEval 2017\nShared Task (Nangia et al., 2017)). Moreover, they achieve the new\nstate-of-the-art encoding result on the original SNLI dataset (Bowman et al.,\n2015).","url_abs":"http://arxiv.org/abs/1708.02312v2","url_pdf":"http://arxiv.org/pdf/1708.02312v2.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":"shortcut-stacked-sentence-encoders-for-multi","repo_url":"https://github.com/easonnie/multiNLI_encoder","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"shortcut-stacked-sentence-encoders-for-multi","repo_url":"https://github.com/DorinK/Implementing-an-SNLI-Paper","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"shortcut-stacked-sentence-encoders-for-multi","repo_url":"https://github.com/KhenAharon/Deep-Learning-SNLI-Residual-Stacked-Encoders","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"600D Residual stacked encoders","rank_in_archive_order":63,"of":98,"metrics":{"% Test Accuracy":"86.0","% Train Accuracy":"91.0","Parameters":"29m"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"300D Residual stacked encoders","rank_in_archive_order":67,"of":98,"metrics":{"% Test Accuracy":"85.7","% Train Accuracy":"89.8","Parameters":"9.7m"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.02312","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}