contextualized-topic-models:一个用于运行上下文化主题建模的python包。 CTM将BERT与主题模型结合在一起以获得一致的主题。还支持多语言任务。跨语言零射击模型发布于EACL 2021

上传者: 42162216 | 上传时间: 2022-08-13 12:32:38 | 文件大小: 31.14MB | 文件类型: ZIP
情境化主题模型 上下文化主题模型(CTM)是一系列主题模型,这些主题模型使用语言的预训练表示形式(例如BERT)来支持主题建模。有关详细信息,请参见论文: Bianchi,F.,Terragni,S.,Hovy,D.,Nozza,D.,&Fersini,E.(2021)。具有零镜头学习功能的跨语言情境主题模型。 EACL。 Bianchi,F.,Terragni,S.和Hovy,D.(2020年)。预培训是一个热门话题:上下文化文档嵌入可提高主题一致性 具有上下文嵌入的主题建模 我们的新主题建模系列支持许多不同的语言(即,HuggingFace模型支持的一种),并有两个版本: CombinedTM将上下文嵌入与旧的单词组合在一起,以使主题更连贯; ZeroShotTM是完成任务的理想主题模型,在该模型中,您可能在测试数据中缺少单词,并且,如果经过多语言嵌入训练,则可以继承多语言主题模型

文件下载

资源详情

[{"title":"( 61 个子文件 31.14MB ) contextualized-topic-models:一个用于运行上下文化主题建模的python包。 CTM将BERT与主题模型结合在一起以获得一致的主题。还支持多语言任务。跨语言零射击模型发布于EACL 2021","children":[{"title":"contextualized-topic-models-master","children":[{"title":"setup.py <span style='color:#111;'> 1.51KB </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 1.18KB </span>","children":null,"spread":false},{"title":"readthedocs.yml <span style='color:#111;'> 569B </span>","children":null,"spread":false},{"title":"requirements.txt <span style='color:#111;'> 151B </span>","children":null,"spread":false},{"title":"Makefile <span style='color:#111;'> 2.20KB </span>","children":null,"spread":false},{"title":"contextualized_topic_models","children":[{"title":"evaluation","children":[{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"rbo","children":[{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"rbo.py <span style='color:#111;'> 10.39KB </span>","children":null,"spread":false}],"spread":true},{"title":"measures.py <span style='color:#111;'> 10.88KB </span>","children":null,"spread":false}],"spread":true},{"title":"contextualized_topic_models.py <span style='color:#111;'> 19B </span>","children":null,"spread":false},{"title":"data","children":[{"title":"gnews","children":[{"title":"train.txt.pkl <span style='color:#111;'> 1.10MB </span>","children":null,"spread":false},{"title":"GoogleNews.txt <span style='color:#111;'> 463.75KB </span>","children":null,"spread":false},{"title":"vocab.pkl <span style='color:#111;'> 131.44KB </span>","children":null,"spread":false},{"title":"bert_embeddings_gnews <span style='color:#111;'> 32.54MB </span>","children":null,"spread":false}],"spread":true},{"title":"sample_text_document <span style='color:#111;'> 85B </span>","children":null,"spread":false}],"spread":true},{"title":"datasets","children":[{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"dataset.py <span style='color:#111;'> 1.12KB </span>","children":null,"spread":false}],"spread":true},{"title":"__init__.py <span style='color:#111;'> 154B </span>","children":null,"spread":false},{"title":"networks","children":[{"title":"inference_network.py <span style='color:#111;'> 4.88KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"decoding_network.py <span style='color:#111;'> 5.27KB </span>","children":null,"spread":false}],"spread":true},{"title":"models","children":[{"title":"ctm.py <span style='color:#111;'> 26.23KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false}],"spread":true},{"title":"utils","children":[{"title":"preprocessing.py <span style='color:#111;'> 2.70KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"data_preparation.py <span style='color:#111;'> 8.77KB </span>","children":null,"spread":false},{"title":"early_stopping","children":[{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"CODE_OF_CONDUCT.md <span style='color:#111;'> 3.28KB </span>","children":null,"spread":false},{"title":"LICENSE <span style='color:#111;'> 1.05KB </span>","children":null,"spread":false},{"title":"early_stopping.py <span style='color:#111;'> 2.18KB </span>","children":null,"spread":false}],"spread":false}],"spread":false}],"spread":true},{"title":"MANIFEST.in <span style='color:#111;'> 287B </span>","children":null,"spread":false},{"title":"requirements_dev.txt <span style='color:#111;'> 166B </span>","children":null,"spread":false},{"title":"LICENSE <span style='color:#111;'> 1.05KB </span>","children":null,"spread":false},{"title":"HISTORY.rst <span style='color:#111;'> 2.11KB </span>","children":null,"spread":false},{"title":"setup.cfg <span style='color:#111;'> 430B </span>","children":null,"spread":false},{"title":".github","children":[{"title":"ISSUE_TEMPLATE.md <span style='color:#111;'> 338B </span>","children":null,"spread":false},{"title":"workflows","children":[{"title":"build.yml <span style='color:#111;'> 1.31KB </span>","children":null,"spread":false}],"spread":false}],"spread":true},{"title":"README.rst <span style='color:#111;'> 18.27KB </span>","children":null,"spread":false},{"title":"tests","children":[{"title":"test_contextualized_topic_models.py <span style='color:#111;'> 6.34KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 57B </span>","children":null,"spread":false}],"spread":false},{"title":"AUTHORS.rst <span style='color:#111;'> 252B </span>","children":null,"spread":false},{"title":"CONTRIBUTING.rst <span style='color:#111;'> 3.65KB </span>","children":null,"spread":false},{"title":"docs","children":[{"title":"requirements.txt <span style='color:#111;'> 106B </span>","children":null,"spread":false},{"title":"Makefile <span style='color:#111;'> 628B </span>","children":null,"spread":false},{"title":"index.rst <span style='color:#111;'> 231B </span>","children":null,"spread":false},{"title":"conf.py <span style='color:#111;'> 4.99KB </span>","children":null,"spread":false},{"title":"history.rst <span style='color:#111;'> 28B </span>","children":null,"spread":false},{"title":"authors.rst <span style='color:#111;'> 28B </span>","children":null,"spread":false},{"title":"installation.rst <span style='color:#111;'> 1.23KB </span>","children":null,"spread":false},{"title":"make.bat <span style='color:#111;'> 789B </span>","children":null,"spread":false},{"title":"readme.rst <span style='color:#111;'> 27B </span>","children":null,"spread":false},{"title":"usage.rst <span style='color:#111;'> 806B </span>","children":null,"spread":false},{"title":"ctm.rst <span style='color:#111;'> 605B </span>","children":null,"spread":false},{"title":"contributing.rst <span style='color:#111;'> 33B </span>","children":null,"spread":false}],"spread":false},{"title":"img","children":[{"title":"lm_topic_model_multilingual.png <span style='color:#111;'> 24.04KB </span>","children":null,"spread":false},{"title":"lm_topic_model.pdf <span style='color:#111;'> 28.56KB </span>","children":null,"spread":false},{"title":"lm_topic_model_multilingual.pdf <span style='color:#111;'> 27.55KB </span>","children":null,"spread":false},{"title":"lm_topic_model.png <span style='color:#111;'> 33.06KB </span>","children":null,"spread":false},{"title":"logo.png <span style='color:#111;'> 29.02KB </span>","children":null,"spread":false},{"title":"displaying_topic.png <span style='color:#111;'> 206.46KB </span>","children":null,"spread":false}],"spread":false},{"title":".editorconfig <span style='color:#111;'> 292B </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