{"blog_url":"https://higepon.hatenablog.com/","width":"100%","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fhigepon.hatenablog.com%2Fentry%2F2019%2F02%2F14%2F183717\" title=\"Quora \u30b3\u30f3\u30da\u5165\u8cde\u8005\u624b\u6cd5\u307e\u3068\u3081 - higepon blog\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","author_url":"https://blog.hatena.ne.jp/higepon/","blog_title":"higepon blog","description":"\u81ea\u5206\u306e\u30b3\u30e1\u30f3\u30c8\u306f\u304b\u306a\u308a\u9069\u5f53\u3002\u5f8c\u3067\u66f4\u65b0\u3059\u308b\u304b\u3082\u3002 3rd 3rd place kernel | Kaggle Keras embedding load \u6642\u306b stemmer and lemmetizer \u3057\u3066\u3067\u304d\u308b\u3060\u3051 dictionary \u306e\u4e2d\u304b\u3089\u898b\u3064\u3051\u308b bidirectional GRU \u3068 LSTM \u306e output \u306e maxpool \u3092 concat max_length = 55 \u3068\u77ed\u3081 Local solid CV to tune all the hyperparameters \u3068\u66f8\u3044\u3066\u3042\u308b\u304c\u3069\u3053\u3060\u308d\u3046 13th 13th place solution | Kaggle Kera\u2026","title":"Quora \u30b3\u30f3\u30da\u5165\u8cde\u8005\u624b\u6cd5\u307e\u3068\u3081","image_url":null,"categories":[],"url":"https://higepon.hatenablog.com/entry/2019/02/14/183717","published":"2019-02-14 18:37:17","height":"190","provider_url":"https://hatena.blog","provider_name":"Hatena Blog","type":"rich","author_name":"higepon","version":"1.0"}