{"blog_title":"ptoolis\u306e\u65e5\u8a18","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fptoolis.hatenadiary.org%2Fentry%2F20080907%2F1220749648\" title=\"Training Tree Transducers - ptoolis\u306e\u65e5\u8a18\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","title":"Training Tree Transducers","author_name":"ptoolis","author_url":"https://blog.hatena.ne.jp/ptoolis/","version":"1.0","width":"100%","description":"Graehl, Knight, May\u306e\u8ad6\u6587\u304cComputational Linguistics\u3068\u8a00\u3046\u96d1\u8a8c\u306b\u767a\u8868\u3055\u308c\u307e\u3057\u305f\u30024. Extended LHS Tree Transducers A weighted extended lhs top-down tree transducer M is a quintuple (sigma, delta, Q, Qi, R). Sigma is the input alphabet, delta the output alphabet, Q the set of states, Qi the initial state, and R the set \u2026","published":"2008-09-07 10:07:28","provider_name":"Hatena Blog","type":"rich","blog_url":"https://ptoolis.hatenadiary.org/","image_url":null,"url":"https://ptoolis.hatenadiary.org/entry/20080907/1220749648","categories":[],"height":"190","provider_url":"https://hatena.blog"}