{"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/learning-natural-language-inference-using","title":"Learning Natural Language Inference using Bidirectional LSTM model and Inner-Attention","arxiv_id":"1605.09090","date":"2016-05-30","proceeding":null,"authors":["Yang Liu","Chengjie Sun","Lei Lin","Xiaolong Wang"],"abstract":"In this paper, we proposed a sentence encoding-based model for recognizing\ntext entailment. In our approach, the encoding of sentence is a two-stage\nprocess. Firstly, average pooling was used over word-level bidirectional LSTM\n(biLSTM) to generate a first-stage sentence representation. Secondly, attention\nmechanism was employed to replace average pooling on the same sentence for\nbetter representations. Instead of using target sentence to attend words in\nsource sentence, we utilized the sentence's first-stage representation to\nattend words appeared in itself, which is called \"Inner-Attention\" in our paper\n. Experiments conducted on Stanford Natural Language Inference (SNLI) Corpus\nhas proved the effectiveness of \"Inner-Attention\" mechanism. With less number\nof parameters, our model outperformed the existing best sentence encoding-based\napproach by a large margin.","url_abs":"http://arxiv.org/abs/1605.09090v1","url_pdf":"http://arxiv.org/pdf/1605.09090v1.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":"learning-natural-language-inference-using","repo_url":"https://github.com/Smerity/keras_snli","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"learning-natural-language-inference-using","repo_url":"https://github.com/songyang0716/NLP/blob/master/natural_language_inference/BiLSTM_encoders_with_intra-attention/model.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"average-pooling","method_name":"Average Pooling"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"600D (300+300) BiLSTM encoders with intra-attention and symbolic preproc.","rank_in_archive_order":74,"of":98,"metrics":{"% Test Accuracy":"85.0","% Train Accuracy":"85.9","Parameters":"2.8m"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"600D (300+300) BiLSTM encoders with intra-attention","rank_in_archive_order":81,"of":98,"metrics":{"% Test Accuracy":"84.2","% Train Accuracy":"84.5","Parameters":"2.8m"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"600D (300+300) BiLSTM encoders","rank_in_archive_order":85,"of":98,"metrics":{"% Test Accuracy":"83.3","% Train Accuracy":"86.4","Parameters":"2.0m"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1605.09090","atlas_url":"https://app.syntology.ai/?focus=1605.09090","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}