等不及馬丁新作，人工智能續寫《冰與火之歌》！想看戳這裏

爲了給苦苦等待的粉絲們找點樂趣，軟件工程師扎克·圖特（Zack Thoutt）讓循環神經網絡人工智能技術學習該劇原著《冰與火之歌》前五部的內容，然後續寫五章劇情。這些人工智能創作的情節與粉絲早前的一些推測部分吻合，比如，詹姆最終殺死了瑟曦，囧雪成了龍騎士，而瓦里斯毒死了龍母。如果你感興趣，可以在GitHub的主頁上查看所有章節。

下面來了解一下人工智能是如何做到的：

After feeding a type of AI known as a recurrent neural network the roughly 5,000 pages of Martin's five previous books, software engineer Zack Thoutt has used the algorithm to predict what will happen next.
軟件工程師扎克·圖特讓一種名爲循環神經網絡的人工智能技術學習了《冰與火之歌》前五部近5000頁的內容，然後利用該算法預測接下來的情節。

According to the AI's predictions, some long-held fan theories do play out - in the five chapters generated by the algorithm so far, Jaime ends up killing Cersei, Jon rides a dragon, and Varys poisons Daenerys.
根據人工智能的預測，一些粉絲早前的推測的確出現了。在該算法目前撰寫的五章內容中，詹姆最終殺死了瑟曦，囧雪成了龍騎士，而瓦里斯毒死了龍母。

如果你感興趣，可以在GitHub的主頁上查看所有章節。附上傳送門：

Each chapter starts with a character's name, just like Martin's actual books.
和馬丁本人撰寫的小說一樣，每章打頭的文字都是一個角色的名字。

But in addition to backing up what many of us already suspect will happen, the AI also introduces some fairly unexpected plot turns that we're pretty sure aren't going to be mirrored in either the TV show or Martin's books, so we wouldn't get too excited just yet.
不過，我們也不要太過興奮，因爲除了存在很多人已經預測會發生的劇情外，這個人工智能算法還引入了一些令人意外的情節，它們絕對不會出現在電視劇或馬丁的小說中。

For example, in the algorithm's first chapter, written from Tyrion's perspective, Sansa turns out to be a Baratheon.
例如，算法編寫的第一章從小惡魔的視角寫道，珊莎其實屬於拜拉席恩家族。

There's also the introduction of a strange, pirate-like new character called Greenbeard.
書中還出現了一個名叫Greenbeard的怪咖，這個新角色的身份和海盜類似。

"It's obviously not perfect," Thoutt told Sam Hill over at Motherboard. "It isn't building a long-term story and the grammar isn't perfect. But the network is able to learn the basics of the English language and structure of George R.R. Martin's style on its own."
圖特在接受Motherboard採訪時告訴山姆•希爾，“這個算法顯然並不完美，它不能編寫長篇故事，語法也有問題。但是神經網絡可以自學英語的基本語言知識以及馬丁的文風結構。”

Neural networks are a type of machine learning algorithm that are inspired by the human brain's ability to not just memorize and follow instructions, but actually learn from past experiences.
神經網絡是一種機器學習算法，設計靈感來自於人腦的記憶能力、遵循指令的能力以及從過去經驗學習的能力。

A recurrent neural network is a specific subclass, which works best when it comes to processing long sequences of data, such as lengthy text from five previous books.
一個循環神經網絡是一個特定的子集，最擅長處理長的數據序列，比如《冰與火之歌》前5部冗長的文本。

In theory, Thoutt's algorithm should be able to create a true sequel to Martin's existing work, based off things that have already happened in the novels.
理論上，圖特的算法應該能基於書中已經出現的劇情創作出《冰與火之歌》真正的續集。

But in practice, the writing is clumsy and, most of the time, nonsensical. And it also references characters that have already died.
但實際上，這個算法的寫作能力還很低級，大部分內容都不知所云，還會提到已經死掉的角色。

Still, some of the lines sound fairly prophetic:
不過，有些臺詞還是有一定預言性的：

"Arya saw Jon holding spears. Your grace," he said to an urgent maid, afraid. "The crow's eye would join you.
他對一個焦急的女僕說，“陛下，艾莉亞看到雪諾拿着長矛。烏鴉的眼睛會跟着你。”

"A perfect model would take everything that has happened in the books into account and not write about characters being alive when they died two books ago," Thoutt told Motherboard.
圖特告訴Motherboard：“完美的算法模型能把書中的所有劇情考慮在內，且不會再讓兩部以前去世的角色再次復活。”

"The reality, though, is that the model isn't good enough to do that. If the model were that good authors might be in trouble ... but it makes a lot of mistakes because the technology to train a perfect text generator that can remember complex plots over millions of words doesn't exist yet."
“然而，實際上這個算法現在還不夠完善。如果它有那麼完美的話，作家們可能就要丟飯碗了……完美的文字創作機器可以記住數百萬字的複雜劇情，現在的技術還不能訓練出這種功能，它會犯很多錯誤。”

One of the main limitations here is the fact that the books just don't contain enough data for an algorithm.
最主要的侷限之一是書中包含的數據對一個算法而言是不夠的。

Although anyone who's read them will testify that they're pretty damn long, they actually represent quite a small data set for a neural network to learn from.
雖然《冰與火之歌》的讀者都認爲這部小說太長了，但是對於神經網絡要學習的數據集來說，這些內容太少了。

But at the same time they contain a whole lot of unique words, nouns, and adjectives which aren't reused, which makes it very hard for the neural network to learn patterns.|
此外，書中包含了許多獨特的詞彙、名詞和形容詞，它們沒有重複出現，這使得神經網絡很難學習到模式。

Thoutt told Hill that a better source would be a book 100 times longer, but with the level of vocabulary of a children's book.
圖特告訴希爾，更合適的數據源是一本比《冰與火之歌》長100倍，且詞彙水平相當於兒童圖書的書籍。