Skip to main content current edition: International edition The Guardian - Back to home Become a supporter Subscribe Find a job Jobs Sign in Search Show More Close with google sign in become a supporter subscribe search find a job dating more from the guardian: change edition: edition International edition The Guardian - Back to home browse all sections close Google Google AI project writes poetry which could make a Vogon proud Inspired by thousands of romantic novels, technique creates verse that rivals that of Douglas Adams’s Vogons A pile of poetry books on a white background.
 succeed in maintaining a sort of theme.
 Photograph: Ian M Butterfield (Concepts)/Alamy Google Google AI project writes poetry which could make a Vogon proud Inspired by thousands of romantic novels, technique creates verse that rivals that of Douglas Adams’s Vogons Samuel Gibbs Tue 17 May ‘16 12.
01 BST Last modified on Wed 22 Feb ‘17 17.
50 GMT This article is 1 year old After its attempts to digest romance novels, one of Google’s artificial intelligence projects is now accidentally writing poetry, some of which would make the fictional Vogons proud.
 there is no one else in the world.
 there is no one else in sight.
 they were the only ones who mattered.
 they were the only ones left.
 he had to be with me.
 she had to be with him.
 i had to do this.
 i wanted to kill him.
 i started to cry.
 i turned to him.
 Google is working with Stanford University and University of Massachusetts in the US to enhance the natural language skills of an AI technique called recurrent neural network language model (RNNLM), which is used within machine translation and image captioning among other tasks.
 It essentially builds sentences a single word at a time by analysing the previous words in that sentence.
 Poetry expresses what it is to be human – it’s therapy for the soul | Adam O’Riordan Read more Currently, RNNLM is not capable of implementing global themes or features, such as a set topic, within its sentence generation.
 Each sentence produced by the algorithms doesn’t necessarily flow smoothly into the next.
 The work, published as a paper through Cornell University’s open scientific paper archive, arXiv, details the researcher’s efforts to add the ability to apply a global theme to sentence generation using a system called a variational autoencoder and the results, including what could easily be mistaken for poetry.
 Some of it would arguably give Douglas Adams a run for his money, as the creator of the Vogons, the Hitchhiker’s Guide to the Galaxy and its Ode to a Small Lump of Green Putty I Found in My Armpit One Midsummer Morning, during a recital of which “four of the audience members died of internal haemorrhaging and the president of the Mid-Galactic Arts Nobbling Council survived only by gnawing one of his own legs off”, according to the book.
 The researchers fed the system starting and ending sentences and then asked it to fill in the gap.
 Below, the bolded text is what the researchers gave the algorithm and the text in between is what it produced.
 The results are generated by the machine based on what it learnt from thousands of romance novels, which made some of the topics “rather dramatic”, according to the authors of the paper.
 he was silent for a long moment.
 he was silent for a moment.
 it was quiet for a moment.
 it was dark and cold.
 there was a pause.
 it was my turn.
 this was the only way.
 it was the only way.
 it was her turn to blink.
 it was hard to tell.
 it was time to move on.
 he had to do it again.
 they all looked at each other.
 they all turned to look back.
 they both turned to face him.
 they both turned and walked away.
 The generated sentences make grammatical sense, maintain a sort of theme and for the most part fit with the start and end sentence.
 Others weren’t quite as poetic, but still maintain the theme set by the start and ending sentences.
 no.
 he said.
 “no,” he said.
 “no,” i said.
 “i know,” she said.
 “thank you,” she said.
 “come with me,” she said.
 “talk to me,” she said.
 “don’t worry about it,” she said.
 i don’t like it, he said.
 i waited for what had happened.
 it was almost thirty years ago.
 it was over thirty years ago.
 that was six years ago.
 he had died two years ago.
 ten, thirty years ago.
 “it’s all right here.
 “everything is all right here.
 “it’s all right here.
 it’s all right here.
 we are all right here.
 come here in five minutes.
 The results show interesting improvements in the ability of the machine to generate sentences that make sense together, which could led to much more human-like interactions with AI chatbots, perhaps even Google’s Now.
 Topics more on this story World's best Go player flummoxed by Google’s ‘godlike’ AlphaGo AI Ke Jie, who once boasted he would never be beaten by a computer at the ancient Chinese game, said he had ‘horrible experience’ Published: 23 May 2017 World's best Go player flummoxed by Google’s ‘godlike’ AlphaGo AI Artificial intelligence 'judge' developed by UCL computer scientists Software program can weigh up legal evidence and moral questions of right and wrong to predict the outcome of trials Published: 24 Oct 2016 Artificial intelligence 'judge' developed by UCL computer scientists Stephen Hawking: AI will be 'either best or worst thing' for humanity Professor praises creation of Cambridge University institute to study future of artificial intelligence Published: 19 Oct 2016 Stephen Hawking: AI will be 'either best or worst thing' for humanity Google creates AI program that uses reasoning to navigate the London tube Combining external memory and deep learning, DeepMind’s program learns how to do tasks independently, and could pave the way for sophisticated AI assistants Published: 12 Oct 2016 Google creates AI program that uses reasoning to navigate the London tube + Machine logic: our lives are ruled by big tech's 'decisions by data' Julia Powles in Berlin Published: 8 Oct 2016 Machine logic: our lives are ruled by big tech's 'decisions by data' + James Lovelock: ‘Before the end of this century, robots will have taken over’ Published: 30 Sep 2016 James Lovelock: ‘Before the end of this century, robots will have taken over’ + How can we address real concerns over artificial intelligence?
 Harry Armstrong and Jared Robert Keller Published: 15 Sep 2016 How can we address real concerns over artificial intelligence?
 + Artificial intelligence: ‘We’re like children playing with a bomb’ Published: 12 Jun 2016 Artificial intelligence: ‘We’re like children playing with a bomb’ most viewed The Guardian back to top all sections close back to top All rights reserved.