{"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/attention-boosted-sequential-inference-model","title":"Attention Boosted Sequential Inference Model","arxiv_id":"1812.01840","date":"2018-12-05","proceeding":null,"authors":["Guanyu Li","Pengfei Zhang","Caiyan Jia"],"abstract":"Attention mechanism has been proven effective on natural language processing.\nThis paper proposes an attention boosted natural language inference model named\naESIM by adding word attention and adaptive direction-oriented attention\nmechanisms to the traditional Bi-LSTM layer of natural language inference\nmodels, e.g. ESIM. This makes the inference model aESIM has the ability to\neffectively learn the representation of words and model the local subsentential\ninference between pairs of premise and hypothesis. The empirical studies on the\nSNLI, MultiNLI and Quora benchmarks manifest that aESIM is superior to the\noriginal ESIM model.","url_abs":"http://arxiv.org/abs/1812.01840v2","url_pdf":"http://arxiv.org/pdf/1812.01840v2.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":[],"tasks":[{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"esim","method_name":"ESIM"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/natural-language-inference-on-multinli","task":"Natural Language Inference","dataset":"MultiNLI","model":"aESIM","rank_in_archive_order":47,"of":67,"metrics":{"Matched":"73.9 ","Mismatched":"73.9"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-quora-question","task":"Natural Language Inference","dataset":"Quora Question Pairs","model":"aESIM","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"88.01"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"aESIM","rank_in_archive_order":39,"of":98,"metrics":{"% Test Accuracy":"88.1"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}