{"provider_url":"https://hatena.blog","categories":["\u6df1\u5c64\u5b66\u7fd2\u306b\u3088\u308b\u81ea\u7136\u8a00\u8a9e\u51e6\u7406"],"url":"https://p180.hatenablog.com/entry/2018/09/24/122155","blog_title":"\u9b3c\u57ce\u8ad6","type":"rich","provider_name":"Hatena Blog","height":"190","title":"Using the Output Embedding to Improve Language Models","version":"1.0","image_url":null,"width":"100%","blog_url":"https://p180.hatenablog.com/","author_url":"https://blog.hatena.ne.jp/p180/","author_name":"p180","description":"[1608.05859] Using the Output Embedding to Improve Language Models \u4ee5\u4e0b\u306e\u8ad6\u6587\u3068\u4e00\u7dd2\u306b\u8a00\u53ca\u3055\u308c\u308b\u3053\u3068\u304c\u591a\u3044 Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling","published":"2018-09-24 12:21:55","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fp180.hatenablog.com%2Fentry%2F2018%2F09%2F24%2F122155\" title=\"Using the Output Embedding to Improve Language Models - \u9b3c\u57ce\u8ad6\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>"}