{"resolved":true,"match_type":"uuid","source_type":"original_book","book_id":"cf76bc49-7e9b-4f42-bee8-3050a9fb9feb","title":"智慧的疆界 从图灵机到人工智能","author":null,"edition":null,"publisher":null,"year":null,"isbn":"9787111778004","requested_by":"printed_page","book":{"source_type":"original_book","book_id":"cf76bc49-7e9b-4f42-bee8-3050a9fb9feb","id":"cf76bc49-7e9b-4f42-bee8-3050a9fb9feb","uuid":"cf76bc49-7e9b-4f42-bee8-3050a9fb9feb","title":"智慧的疆界 从图灵机到人工智能","normalized_title":"智慧的疆界从图灵机到人工智能","author":null,"edition":null,"publisher":null,"year":null,"isbn":"9787111778004","isbns":["9787111778004","9787111695714"],"parsed":true,"ai_readable":true,"document_type":"book","page_count":456,"navigation_url":"https://workshop.closeclaw.top/ai/book/cf76bc49-7e9b-4f42-bee8-3050a9fb9feb","title_url":"https://workshop.closeclaw.top/ai/title/%E6%99%BA%E6%85%A7%E7%9A%84%E7%96%86%E7%95%8C%20%E4%BB%8E%E5%9B%BE%E7%81%B5%E6%9C%BA%E5%88%B0%E4%BA%BA%E5%B7%A5%E6%99%BA%E8%83%BD","fixed_page_url_template":"https://workshop.closeclaw.top/ai/book/cf76bc49-7e9b-4f42-bee8-3050a9fb9feb/page/{printed_page}","path_api_url_template":"https://workshop.closeclaw.top/api/ai/book/cf76bc49-7e9b-4f42-bee8-3050a9fb9feb/page/{printed_page}","read_url":"https://workshop.closeclaw.top/api/ai/read/cf76bc49-7e9b-4f42-bee8-3050a9fb9feb","page_url":"https://workshop.closeclaw.top/api/ai/books/cf76bc49-7e9b-4f42-bee8-3050a9fb9feb/page","search_url":"https://workshop.closeclaw.top/api/ai/books/cf76bc49-7e9b-4f42-bee8-3050a9fb9feb/search"},"page":{"printed_page":328,"pdf_page":343,"physical_index":343,"physical_index_base":0,"printed_page_status":"recognized","page_sha256":"d619f3d5b7bd1d1058690494ad38adc4aeaa19781d9b84d26fd4abda3a27a6c1"},"chapter":"内容简介","content":"在解码器一侧的任务是对输出序列中下一个词的最大概率进行预测，这个任务同时接收两个输入，一个是编码器给出的上下文向量（Context Vector），另一个是上一轮解码器刚刚输出的结果（否则就谈不上是“下一个”词了）。刚刚开始时，首个输入词固定为起始标志“ <Start>”。笔者举个例子来说明解码器是如何工作的：假设当前进行的是机器翻译任务，上一阶段编码器已经对输入序列“好好学习”产生了上下文向量，这个上下文向量在论文中被称为“隐藏状态”（Hidden Status，HS）。当解码器接到隐藏状态 HS1 和第一个词“ <Start>”后，产生的输出是“ good”，每轮产生输出词的同时也会修正隐藏状态的内容，如将隐藏状态 HS1 修正成 HS2。接下来，把上一轮输出的词“ good”和 HS2 作为输入，本轮产生的输出同样是“ good”并修改隐藏状态为 HS3，然后第三轮根据第二个“ good”产生了“ study”，最后产生结束标记“ <End>”，由此就生成了完整的翻译结果“ <Start>”“ good”\n\n328\n\n第三部分 第三波高潮\n\n○一 “ Eficient Estimation of Word Representations in Vector Space ” 和“ Distributed Representationsof Words and Phrases and their Compositionality ”，苏茨克维本人参与了相关工作，是论文的第二作者。","previous_page":327,"next_page":329}