Document-Transformer:使用文档级上下文改进Transformer转换模型

上传者: 42139429 | 上传时间: 2022-04-30 16:44:38 | 文件大小: 308KB | 文件类型: ZIP
使用文档级上下文改进变压器翻译模型 内容 介绍 这是我们工作的实现,将Transformer扩展为集成文档级上下文[ ]。 该实现在 用法 注意:用法不是用户友好的。 以后可能会改善。 训练标准的变压器模型,请参考的用户手册。 假设model_baseline / model.ckpt-30000在验证集上表现最佳。 使用以下命令生成虚拟的改进的Transformer模型: python THUMT/thumt/bin/trainer_ctx.py --inputs [source corpus] [target corpus] \ --context [context corpus] \ --vocabulary [source

文件下载

资源详情

[{"title":"( 48 个子文件 308KB ) Document-Transformer:使用文档级上下文改进Transformer转换模型","children":[{"title":"Document-Transformer-master","children":[{"title":"LICENSE <span style='color:#111;'> 1.50KB </span>","children":null,"spread":false},{"title":"thumt","children":[{"title":"interface","children":[{"title":"__init__.py <span style='color:#111;'> 204B </span>","children":null,"spread":false},{"title":"model.py <span style='color:#111;'> 1.90KB </span>","children":null,"spread":false}],"spread":true},{"title":"data","children":[{"title":"__init__.py <span style='color:#111;'> 50B </span>","children":null,"spread":false},{"title":"record.py <span style='color:#111;'> 5.20KB </span>","children":null,"spread":false},{"title":"cache.py <span style='color:#111;'> 893B </span>","children":null,"spread":false},{"title":"dataset.py <span style='color:#111;'> 15.93KB </span>","children":null,"spread":false},{"title":"vocab.py <span style='color:#111;'> 747B </span>","children":null,"spread":false}],"spread":true},{"title":"bin","children":[{"title":"trainer.py <span style='color:#111;'> 14.24KB </span>","children":null,"spread":false},{"title":"trainer_ctx.py <span style='color:#111;'> 14.56KB </span>","children":null,"spread":false},{"title":"translator_ctx.py <span style='color:#111;'> 11.39KB </span>","children":null,"spread":false},{"title":"translator.py <span style='color:#111;'> 10.81KB </span>","children":null,"spread":false},{"title":"scorer.py <span style='color:#111;'> 8.54KB </span>","children":null,"spread":false}],"spread":true},{"title":"__init__.py <span style='color:#111;'> 50B </span>","children":null,"spread":false},{"title":"layers","children":[{"title":"rnn_cell.py <span style='color:#111;'> 4.86KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 133B </span>","children":null,"spread":false},{"title":"attention.py <span style='color:#111;'> 13.32KB </span>","children":null,"spread":false},{"title":"nn.py <span style='color:#111;'> 5.91KB </span>","children":null,"spread":false}],"spread":true},{"title":"models","children":[{"title":"rnnsearch.py <span style='color:#111;'> 14.42KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 754B </span>","children":null,"spread":false},{"title":"seq2seq.py <span style='color:#111;'> 6.92KB </span>","children":null,"spread":false},{"title":"transformer.py <span style='color:#111;'> 14.95KB </span>","children":null,"spread":false},{"title":"contextual_transformer.py <span style='color:#111;'> 23.21KB </span>","children":null,"spread":false}],"spread":true},{"title":"utils","children":[{"title":"inference_ctx.py <span style='color:#111;'> 12.80KB </span>","children":null,"spread":false},{"title":"sample.py <span style='color:#111;'> 160B </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 50B </span>","children":null,"spread":false},{"title":"inference.py <span style='color:#111;'> 11.62KB </span>","children":null,"spread":false},{"title":"hooks.py <span style='color:#111;'> 13.12KB </span>","children":null,"spread":false},{"title":"optimize.py <span style='color:#111;'> 5.35KB </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 314B </span>","children":null,"spread":false},{"title":"bleu.py <span style='color:#111;'> 2.97KB </span>","children":null,"spread":false},{"title":"parallel.py <span style='color:#111;'> 3.65KB </span>","children":null,"spread":false}],"spread":true},{"title":"scripts","children":[{"title":"compare.py <span style='color:#111;'> 1.68KB </span>","children":null,"spread":false},{"title":"convert_old_model.py <span style='color:#111;'> 4.79KB </span>","children":null,"spread":false},{"title":"combine.py <span style='color:#111;'> 2.79KB </span>","children":null,"spread":false},{"title":"change.py <span style='color:#111;'> 2.37KB </span>","children":null,"spread":false},{"title":"input_converter.py <span style='color:#111;'> 4.77KB </span>","children":null,"spread":false},{"title":"check_param.py <span style='color:#111;'> 1.17KB </span>","children":null,"spread":false},{"title":"build_vocab.py <span style='color:#111;'> 2.25KB </span>","children":null,"spread":false},{"title":"checkpoint_averaging.py <span style='color:#111;'> 3.91KB </span>","children":null,"spread":false},{"title":"shuffle_corpus.py <span style='color:#111;'> 1.29KB </span>","children":null,"spread":false},{"title":"convert_vocab.py <span style='color:#111;'> 493B </span>","children":null,"spread":false},{"title":"combine_add.py <span style='color:#111;'> 2.83KB </span>","children":null,"spread":false}],"spread":false}],"spread":true},{"title":"README.md <span style='color:#111;'> 4.21KB </span>","children":null,"spread":false},{"title":"docs","children":[{"title":"everb.sty <span style='color:#111;'> 65.42KB </span>","children":null,"spread":false},{"title":"UserManual.tex <span style='color:#111;'> 27.31KB </span>","children":null,"spread":false},{"title":"thumt.bib <span style='color:#111;'> 4.44KB </span>","children":null,"spread":false}],"spread":true},{"title":"UserManual.pdf <span style='color:#111;'> 207.75KB </span>","children":null,"spread":false}],"spread":true}],"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