Deep-Speeling:深度学习神经网络可纠正拼写

上传者: 42166105 | 上传时间: 2022-10-04 17:29:45 | 文件大小: 93.39MB | 文件类型: ZIP
深刺 使用深度学习纠正拼写错误 动机 该项目的灵感来自在上发表的文章。 可以在Github上找到他的代码。 2017年1月,我开始了并且从第一堂课开始就迷上了。 以前,我曾多次听到过“神经网络”一词,并且对它们可以完成的事情有一个大致的了解,但从未对它们的“工作原理”有所了解。 自完成课程以来,我没有太多机会来尝试这项技术,但是我一直在考虑它的用途,尤其是在信息检索领域,这是我过去十年来一直致力于的领域。 除非您是Google,否则纠正拼写错误的典型技术是,或者它的近亲是。 魏斯先生很好地解释了为什么这些方法效果不佳。 目标 使用Tensorflow重新实现Weiss先生的递归神经网络(RNN),并达到相同的准确性水平。 他建议尝试实施某些探索领域以及其他领域,以查看是否可以获得进一步的改进。 编码 该代码的第一部分主要涉及下载Google发布的并对其进行设置,以进行培训,而这主要是

文件下载

资源详情

[{"title":"( 42 个子文件 93.39MB ) Deep-Speeling:深度学习神经网络可纠正拼写","children":[{"title":"Deep-Speeling-master","children":[{"title":"large_graph","children":[{"title":"graph_params <span style='color:#111;'> 3B </span>","children":null,"spread":false},{"title":"sourceinttoletter.json <span style='color:#111;'> 765B </span>","children":null,"spread":false},{"title":"best_model.ckpt.index <span style='color:#111;'> 1.52KB </span>","children":null,"spread":false},{"title":"targetinttoletter.json <span style='color:#111;'> 743B </span>","children":null,"spread":false},{"title":"targetlettertoint.json <span style='color:#111;'> 609B </span>","children":null,"spread":false},{"title":"sourcelettertoint.json <span style='color:#111;'> 627B </span>","children":null,"spread":false},{"title":"best_model.ckpt.meta <span style='color:#111;'> 889.94KB </span>","children":null,"spread":false},{"title":"best_model.ckpt.data-00000-of-00001 <span style='color:#111;'> 97.48MB </span>","children":null,"spread":false},{"title":"checkpoint <span style='color:#111;'> 87B </span>","children":null,"spread":false}],"spread":true},{"title":".gitattributes <span style='color:#111;'> 176B </span>","children":null,"spread":false},{"title":"helper.py <span style='color:#111;'> 1.35KB </span>","children":null,"spread":false},{"title":"images","children":[{"title":"targets_after_processing_1.png <span style='color:#111;'> 138.89KB </span>","children":null,"spread":false},{"title":"targets_add_go.png <span style='color:#111;'> 178.09KB </span>","children":null,"spread":false},{"title":"embed_sequence.png <span style='color:#111;'> 254.22KB </span>","children":null,"spread":false},{"title":"sequence-to-sequence-training-decoder.png <span style='color:#111;'> 391.98KB </span>","children":null,"spread":false},{"title":"MarquisdeFavras.jpg <span style='color:#111;'> 36.78KB </span>","children":null,"spread":false},{"title":"strided_slice_1.png <span style='color:#111;'> 211.13KB </span>","children":null,"spread":false},{"title":"sequence-to-sequence-inference-decoder.png <span style='color:#111;'> 412.71KB </span>","children":null,"spread":false},{"title":"source_and_target_arrays.png <span style='color:#111;'> 247.24KB </span>","children":null,"spread":false},{"title":"sequence-to-sequence.jpg <span style='color:#111;'> 36.54KB </span>","children":null,"spread":false},{"title":"target_batch.png <span style='color:#111;'> 174.58KB </span>","children":null,"spread":false},{"title":"logits.png <span style='color:#111;'> 369.81KB </span>","children":null,"spread":false},{"title":"source_batch.png <span style='color:#111;'> 188.25KB </span>","children":null,"spread":false},{"title":"embeddings.png <span style='color:#111;'> 322.47KB </span>","children":null,"spread":false},{"title":"encoder.png <span style='color:#111;'> 195.48KB </span>","children":null,"spread":false},{"title":"targets_1.png <span style='color:#111;'> 151.66KB </span>","children":null,"spread":false}],"spread":false},{"title":"Test dataset accuracy.xlsx <span style='color:#111;'> 38.60KB </span>","children":null,"spread":false},{"title":"requirements.txt <span style='color:#111;'> 882B </span>","children":null,"spread":false},{"title":"small_graph","children":[{"title":"graph_params <span style='color:#111;'> 3B </span>","children":null,"spread":false},{"title":"sourceinttoletter.json <span style='color:#111;'> 335B </span>","children":null,"spread":false},{"title":"targetinttoletter.json <span style='color:#111;'> 335B </span>","children":null,"spread":false},{"title":"targetlettertoint.json <span style='color:#111;'> 275B </span>","children":null,"spread":false},{"title":"sourcelettertoint.json <span style='color:#111;'> 275B </span>","children":null,"spread":false}],"spread":true},{"title":"README.md <span style='color:#111;'> 3.96KB </span>","children":null,"spread":false},{"title":"deep_speeling.py <span style='color:#111;'> 52.28KB </span>","children":null,"spread":false},{"title":"Small data training results.xlsx <span style='color:#111;'> 29.28KB </span>","children":null,"spread":false},{"title":"Training results.xlsx <span style='color:#111;'> 592.69KB </span>","children":null,"spread":false},{"title":"data","children":[{"title":"letters_target.txt <span style='color:#111;'> 49.03KB </span>","children":null,"spread":false},{"title":"letters_source.txt <span style='color:#111;'> 49.03KB </span>","children":null,"spread":false}],"spread":true},{"title":"deep_speeling.ipynb <span style='color:#111;'> 154.68KB </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 1.19KB </span>","children":null,"spread":false},{"title":"output_small.txt <span style='color:#111;'> 50.90KB </span>","children":null,"spread":false}],"spread":false}],"spread":true}]

评论信息

免责申明

【只为小站】的资源来自网友分享,仅供学习研究,请务必在下载后24小时内给予删除,不得用于其他任何用途,否则后果自负。基于互联网的特殊性,【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查;无论 【只为小站】 经营者是否已进行审查,用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场,基于网友分享,根据中国法律《信息网络传播权保护条例》第二十二条之规定,若资源存在侵权或相关问题请联系本站客服人员,zhiweidada#qq.com,请把#换成@,本站将给予最大的支持与配合,做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明