At first glance, you'd be forgiven for mistaking these people as the newest contestants on Love Island. But the glamourous faces aren't actually real, and instead were dreamt up artificial intelligence. Love experts surveyed thousands of Americans on what qualities they find most attractive in a man and woman, including personal style, hair color and more. Then they asked AI to generate image what they would look like based on those answers. The results are actually from two individual stunts by love experts at Shane Co, who generated the ideal boyfriend and ideal girlfriend.

Most women have an'ideal boyfriend' in their minds, but the look and personality seem to depend on which state they live in. Love experts surveyed thousands of Americans on what qualities they find most attractive in a man and asked artificial intelligence to re-imagine what their dream mate would look like based on hair and eye color, hairstyle and personal style. The initial survey found that the ideal boyfriend has blue eyes, short and curly brown hair, and an outdoorsy look without any tattoos or glasses. But residents of each state have a preference - New Jersians envision a man with a fade haircut and an athletic build, and Californians prefer a partner with hazel eyes and tattoos. The love experts at Shane Co. surveyed over 2,100 Americans from across the country on what qualities they find most attractive in a man. The gallery does not include Alaska, Montana, North Dakota, South Dakota, Vermont, and Wyoming due to a lack of respondents.

Posts, as important containers of user-generated-content pieces on social media, are of tremendous social influence and commercial value. As an integral components of a post, the headline has a decisive contribution to the post's popularity. However, current mainstream method for headline generation is still manually writing, which is unstable and requires extensive human effort. This drives us to explore a novel research question: Can we automate the generation of popular headlines on social media? We collect more than 1 million posts of 42,447 celebrities from public data of Xiaohongshu, which is a well-known social media platform in China. We then conduct careful observations on the headlines of these posts. Observation results demonstrate that trends and personal styles are widespread in headlines on social medias and have significant contribution to posts's popularity. Motivated by these insights, we present MEBART, which combines Multiple preference-Extractors with Bidirectional and Auto-Regressive Transformers (BART), capturing trends and personal styles to generate popular headlines on social medias. We perform extensive experiments on real-world datasets and achieve state-of-the-art performance compared with several advanced baselines. In addition, ablation and case studies demonstrate that MEBART advances in capturing trends and personal styles.

Incorporating personal preference is crucial in advanced machine translation tasks. Despite the recent advancement of machine translation, it remains a demanding task to properly reflect personal style. In this paper, we introduce a personalized automatic post-editing framework to address this challenge, which effectively generates sentences considering distinct Figure 1: Example of a personal post-editing triplet personal behaviors. To build this framework, (i.e., source (src), machine translation (mt), and postedit we first collect post-editing data that connotes (pe)) given the source text in English and the translated the user preference from a live machine translation text in Korean. A post-edited sentence does not system. Specifically, real-world users enter only contain error correction of an initial machine translation source sentences for translation and edit result but also reflects individual preference. For the machine-translated outputs according to instance, a human post-editor modifies the word "primarily" the user's preferred style. We then propose to "primary," but also change " 공헌 " to its synonym a model that combines a discriminator module " 기여 " while keeping the rest as it is (e.g., "research").

Every natural text is written in some style. The style is formed by a complex combination of different stylistic factors, including formality markers, emotions, metaphors, etc. Some factors implicitly reflect the author's personality, while others are explicitly controlled by the author's choices in order to achieve some personal or social goal. One cannot form a complete understanding of a text and its author without considering these factors. The factors combine and co-vary in complex ways to form styles. Studying the nature of the covarying combinations sheds light on stylistic language in general, sometimes called cross-style language understanding. This paper provides a benchmark corpus (xSLUE) with an online platform (http://xslue.com) for cross-style language understanding and evaluation. The benchmark contains text in 15 different styles and 23 classification tasks. For each task, we provide the fine-tuned classifier for further analysis. Our analysis shows that some styles are highly dependent on each other (e.g., impoliteness and offense), and some domains (e.g., tweets, political debates) are stylistically more diverse than others (e.g., academic manuscripts). We discuss the technical challenges of cross-style understanding and potential directions for future research: cross-style modeling which shares the internal representation for low-resource or low-performance styles and other applications such as cross-style generation.

It would be nearly impossible for one person – or even a dedicated team – to tease out meaningful trends and insights from such an onslaught of visual data. For an AI (properly trained with the right algorithms), it's a piece of cake, according to Kavita Bala, chair of the computer science department at Cornell University. She and her team used artificial intelligence (AI) to create a map of style trends and influencers by analyzing 14.5 million photos of people shared publicly on social media. Bala's StreetStyle project can answer questions like: How many people wear black in Los Angeles today, compared with two years ago? Or, where in the world is the hijab most prevalent?

At least, that could be the case if the fashionista is a customer of one of several services that offer fashion delivered on demand, such as San Francisco-based startup Stitch Fix. Using data analysis software and machine learning to match users with personalized clothing choices, Stitch Fix is ushering the fashion industry into the age of Big Data. For customers who don't pry too closely into the startup's inner workings, the service is intended to feel like magic. "All they're seeing is they order a box of clothes, and presto -- it appears," said Eric Colson, Stitch Fix's chief algorithms officer. Companies in a variety of industries are relying more heavily on data to provide personalized recommendations -- think Netflix using algorithms to find movies or TV shows users might like, or Amazon suggesting additional purchases based on what's in someone's cart.