{"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/neural-natural-language-inference-models","title":"Neural Natural Language Inference Models Enhanced with External Knowledge","arxiv_id":"1711.04289","date":"2017-11-12","proceeding":"ACL 2018 7","authors":["Qian Chen","Xiaodan Zhu","Zhen-Hua Ling","Diana Inkpen","Si Wei"],"abstract":"Modeling natural language inference is a very challenging task. With the\navailability of large annotated data, it has recently become feasible to train\ncomplex models such as neural-network-based inference models, which have shown\nto achieve the state-of-the-art performance. Although there exist relatively\nlarge annotated data, can machines learn all knowledge needed to perform\nnatural language inference (NLI) from these data? If not, how can\nneural-network-based NLI models benefit from external knowledge and how to\nbuild NLI models to leverage it? In this paper, we enrich the state-of-the-art\nneural natural language inference models with external knowledge. We\ndemonstrate that the proposed models improve neural NLI models to achieve the\nstate-of-the-art performance on the SNLI and MultiNLI datasets.","url_abs":"http://arxiv.org/abs/1711.04289v3","url_pdf":"http://arxiv.org/pdf/1711.04289v3.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":"neural-natural-language-inference-models","repo_url":"https://github.com/lukecq1231/kim","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"neural-natural-language-inference-models","repo_url":"https://github.com/MS-P3/code6/tree/main/inference","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"KIM Ensemble","rank_in_archive_order":22,"of":98,"metrics":{"% Test Accuracy":"89.1","% Train Accuracy":"93.6","Parameters":"43m"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"KIM","rank_in_archive_order":32,"of":98,"metrics":{"% Test Accuracy":"88.6","% Train Accuracy":"94.1","Parameters":"4.3m"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.04289","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}