Analyzing the pattern of semantic variation in long real-world texts such as books or transcripts is interesting from the stylistic, cognitive, and linguistic perspectives. It is also useful for applications such as text segmentation, document summarization, and detection of semantic novelty. The recent emergence of several vector-space methods for sentence embedding has made such analysis feasible. However, this raises the issue of how consistent and meaningful the semantic representations produced by various methods are in themselves. In this paper, we compare several recent sentence embedding methods via time-series of semantic similarity between successive sentences and matrices of pairwise sentence similarity for multiple books of literature. In contrast to previous work using target tasks and curated datasets to compare sentence embedding methods, our approach provides an evaluation of the methods 'in the wild'. We find that most of the sentence embedding methods considered do infer highly correlated patterns of semantic similarity in a given document, but show interesting differences.

In 2017 I decided to find out what would happen if I trained a neural net on 240 Christmas carols (collected by The Times of London and reader/neural net hobbyist Erik Svensson). Run, run Rudolph, run, run Rudolph, run, run Rudolph, run, run Rudolph, run, run Rudolph, run, run Rudolph, run, run Rudolph, run, run Rudolf the new born King. You can kind of understand where the confusion came from. But that was 2017, when I was training char-rnn from scratch on my laptop. Now in 2019 I have access to the much more powerful GPT-2, trained by OpenAI on 40GB of text from the internet.

There's no denying that holiday music is somewhat formulaic. You'd think it would be easy for a computer to generate something indistinguishable from the typical carols piped through department stores this time of year. Turns out, it's not that easy. Swedish company Made by AI recently trained an AI system on 100 midi files of Christmas tunes, then tasked it with creating new songs. Made by AI is not the first group to create some lackluster AI-generated music. There was this attempt, from researchers at the University of Toronto in 2016.

Thankfully, it looks like we're not quite there yet. Colorado-based research scientist Janelle Shane has trained a neural network (a type of machine-learning algorithm) to write its own Christmas carols, and the results are…interesting. Shane trained the algorithm to imitate a set of 240 popular Christmas carols aggregated by the Times of London. The AI trained itself by continuously attempting to write carols, checking their accuracy against the carols in the dataset, and modifying its process accordingly. Here's an excerpt from one, which Shane posted on her blog: The story of the chimney seeSanta baby, and blood and joyous so world and joy and good will to seeSanta baby bore sweet Jesus ChristFa la la la la la la, la la la la la la la la.

Neural networks are a type of computer program that imitate the way that brains learn to solve problems. They're used for face recognition, self-driving cars, language translation, financial decisions, and more. I mainly use them to write humor. My process starts with a dataset - something that the neural network has to figure out how to imitate. Rather unfairly, I give it no instructions about whether it's trying to write knock-knock jokes or invent Halloween costumes or begin a novel.

As we near the dawn of the robot apocalypse, this is proof that you're probably safe for at least a few more weeks. Colorado-based research scientists Janelle Shane recently trained her own neural network to write its own Christmas carols. Using a collection of about 240 carols ranging from "What Child is This?" to "Grandma Got Run Over by a Reindeer," Shane turned the neural net loose with zero instruction. First, it attempted to find patterns in the songs, thus making its own rules of what goes together. From there, it cross-references its creation to existing Christmas (not-so) favorites in an attempt to check its own work. It learns to capitalize letters when they should be capitalized, and to utilize linebreaks to make the creation readable.

A neural network enthusiast has shared the hilarious results of an experiment to let an AI write Christmas carols. With mentions of reindeer, jingle bells, and even some'Fa la la la's', it may have gotten some things right – but, it's doubtful anyone will be singing these songs around the tree. The neural network, starting with no knowledge of what Christmas carols are, created songs filled with bizarre and nonsensical phrases, from'Hurry Christmas to you,' to'Santa baby, and Dancer, and Curry down.' With mentions of reindeer, jingle bells, and even some'Fa la la la's', it may have gotten some things right – but, it's doubtful anyone will be singing these songs around the tree. To train the neural network, Shane fed it roughly 240 carols, collected by the Times of London and reader Erik Svensson.

Christmas is largely about tradition, and sometimes it's nice to watch the same old stuff: movies that celebrate Christmas for all its good qualities, its ability to bring people together and to get some people to be a little bit nicer to one another. The movies here are sure to get the cheer flowing. If you'd rather skip the Christmas carols and good cheer, come back tomorrow when we'll offer our favorite twisted holiday fare. Santa's ne'er-do-well son Arthur (voiced by James McAvoy) gets the chance to save Christmas in Arthur Christmas. Coming from Aardman Animations--the English company that brought us Wallace and Gromit--Arthur Christmas (2011) is one of the most hilarious, colorful, and exciting animated Christmas movies ever made. Arthur (voiced by James McAvoy) is the clumsy, cheery son of Santa Claus; he works in a little, brightly colored office answering letters to children, and he loves his job. His older brother Steve (voiced by Hugh Laurie), on the other hand, pretty much runs the high-tech operation of delivering presents to all the children in the world in one night, while the current Santa Claus (voiced by Jim Broadbent) seems to have reached retirement age.

Artificial intelligence (AI) made incredible strides in 2016, and the growth appears set to accelerate as we enter the New Year. A team of Microsoft researchers has released a dataset of 100,000 questions and answers that other AI researchers can use – for free – in their quest to create systems that can read and answer questions as well as a human. The MS MARCO dataset is based on anonymized real-world data from Bing and Cortana queries and is part of an attempt to spur the breakthroughs in machine reading that are already happening in image and speech recognition. The move is also aimed at facilitating advances toward "artificial general intelligence," or machines that can think like humans – and can read and understand a document as well as a person. Meanwhile, AI helped a musician in Norway sing a new tune for the holidays this year: a Christmas carol that was created by Microsoft's AI technology.

The days leading up to the holiday have been a real roller coaster ride for Cyanogen fans. Yesterday, Cyanogen Inc. unceremoniously pulled the plug on its support for... Read more ... Tim Curry will read you'A Christmas Carol' from your Amazon Echo It's the time of year when we find ourselves together with our loved ones, gathered around the warming seasonal glow of our smart home devices. And for those who managed to... Read more ... Google has been talking about your living room for a long time. We imagine any new tech thing takes a lot of planning, a lot of money, and a lot of time. The push to get Google... Read more ... This video shows what Super Mario Run would look like in... Super Mario Run may have only been out for a week, but that hasn't stopped fans from making Nintendo's automatic runner a reality thanks to cheap costumes and impressive... Read more ...