Abstract: On an artist's profile page, music streaming services frequently recommend a ranked list of "similar artists" that fans also liked. However, implementing such a feature is challenging for new artists, for which usage data on the service (e.g. In this paper, we model this cold start similar artists ranking problem as a link prediction task in a directed and attributed graph, connecting artists to their top-k most similar neighbors and incorporating side musical information. Then, we leverage a graph autoencoder architecture to learn node embedding representations from this graph, and to automatically rank the top-k most similar neighbors of new artists using a gravity-inspired mechanism. We empirically show the flexibility and the effectiveness of our framework, by addressing a real-world cold start similar artists ranking problem on a global music streaming service.
Thoppilan, Romal, De Freitas, Daniel, Hall, Jamie, Shazeer, Noam, Kulshreshtha, Apoorv, Cheng, Heng-Tze, Jin, Alicia, Bos, Taylor, Baker, Leslie, Du, Yu, Li, YaGuang, Lee, Hongrae, Zheng, Huaixiu Steven, Ghafouri, Amin, Menegali, Marcelo, Huang, Yanping, Krikun, Maxim, Lepikhin, Dmitry, Qin, James, Chen, Dehao, Xu, Yuanzhong, Chen, Zhifeng, Roberts, Adam, Bosma, Maarten, Zhao, Vincent, Zhou, Yanqi, Chang, Chung-Ching, Krivokon, Igor, Rusch, Will, Pickett, Marc, Srinivasan, Pranesh, Man, Laichee, Meier-Hellstern, Kathleen, Morris, Meredith Ringel, Doshi, Tulsee, Santos, Renelito Delos, Duke, Toju, Soraker, Johnny, Zevenbergen, Ben, Prabhakaran, Vinodkumar, Diaz, Mark, Hutchinson, Ben, Olson, Kristen, Molina, Alejandra, Hoffman-John, Erin, Lee, Josh, Aroyo, Lora, Rajakumar, Ravi, Butryna, Alena, Lamm, Matthew, Kuzmina, Viktoriya, Fenton, Joe, Cohen, Aaron, Bernstein, Rachel, Kurzweil, Ray, Aguera-Arcas, Blaise, Cui, Claire, Croak, Marian, Chi, Ed, Le, Quoc
We present LaMDA: Language Models for Dialog Applications. LaMDA is a family of Transformer-based neural language models specialized for dialog, which have up to 137B parameters and are pre-trained on 1.56T words of public dialog data and web text. While model scaling alone can improve quality, it shows less improvements on safety and factual grounding. We demonstrate that fine-tuning with annotated data and enabling the model to consult external knowledge sources can lead to significant improvements towards the two key challenges of safety and factual grounding. The first challenge, safety, involves ensuring that the model's responses are consistent with a set of human values, such as preventing harmful suggestions and unfair bias. We quantify safety using a metric based on an illustrative set of human values, and we find that filtering candidate responses using a LaMDA classifier fine-tuned with a small amount of crowdworker-annotated data offers a promising approach to improving model safety. The second challenge, factual grounding, involves enabling the model to consult external knowledge sources, such as an information retrieval system, a language translator, and a calculator. We quantify factuality using a groundedness metric, and we find that our approach enables the model to generate responses grounded in known sources, rather than responses that merely sound plausible. Finally, we explore the use of LaMDA in the domains of education and content recommendations, and analyze their helpfulness and role consistency.
"Drown in the Sun" by Nirvana, "Man, I Know" by Amy Winehouse, "You're Gonna Kill Me" by Jimi Hendrix, and "The Roads Are Alive" by The Doors are the songs featured on the unique compilation The Lost Tapes of the 27 Club. The songs are unique not only because they were created through artificial intelligence, but also because of their message. Will never rise with me to fire" -- sings the singer in Nirvana's "new" song "Drown in the Sun." The lyrics and music are deceptively reminiscent of the original style of Kurt Cobain, who died in 1994, but the musician himself of the "found" song never composed, never wrote the lyrics, and never heard it. "Drown in the Sun" was created through artificial intelligence, and is produced by the non-profit organization Over the Bridge, which with its project The Lost Tapes of the 27 Club wants to draw attention to the issue of mental health among artists. To this end, it has decided to symbolically bring several musicians back to life by resurrecting their music. Using machine learning technology from Google -- namely the Magenta program -- it was possible to create new tracks of musicians who died prematurely by joining the so-called 27 Club. First, the IT specialists fed the computer program an archive of about 30 Nirvana songs. The Magenta program then analyzed the files for repeating components and then developed an entirely new song. However, the vocalist's voice in "Drowed in the Sun" is 100 percent human, assures Eric Hogan, lead singer of Nevermind, an Atlanta-based Nirvana cover band. Apart from the "lost" Nirvana track, The Lost Tapes of the 27 Club project has also created three other pieces, including "Man, I Know" in the style of Amy Winehouse, "The Roads Are Alive" in the style of The Doors and "You're Gonna Kill Me" in the style of Jimi Hendrix's music. All of the musicians whose music has been entrusted to artificial intelligence belong to what is known as the 27 Club. The 27 Club has become a pop culture term for musicians, artists and actors who have died at (or near) the age of 27. Many of them passed away prematurely as a result of battling debilitating addictions. Most also struggled with mental health issues. Kurt Cobain, struggling with heroin addiction, committed suicide in 1994. With its campaign Over the Bridge organization wants to draw attention to the scale of mental problems that artists face. Many of them, unable to cope with their problems, turn to drugs. According to a survey conducted by the organization, as many as 71 percent of musicians report experiencing anxiety and panic attacks, and 68 percent admit that they have struggled with depression. Suicide attempts are also a huge problem. They occur nearly twice as often among musicians and those working in the music industry as in the general population. "As long as there has been popular music, musicians and crews will struggle with mental health problems at levels that far exceed those in the general adult population.
Fans of Nirvana may do a double-take when they hear'Drowned in the Sun,' a new song created by artificial intelligence that simulates the songwriting of late grunge legend Kurt Cobain. Engineers fed Nirvana's back catalog to Google's AI program, Magenta, which analyzed it for recurring components and then developed an entirely new track. The voice on'Drowned in the Sun,' is 100 percent human, though--provided by Eric Hogan, lead singer of the Atlanta Nirvana cover band Nevermind. The song is just one release from The Lost Tapes of the 27 Club, a project developed by the nonprofit Over the Bridge, which spotlights mental health issues in the music industry. Other AI-generated'lost' tracks have taken their cue from Jim Morrison, Jimi Hendrix and Amy Winehouse, who, like Cobain, died at age 27.
What if I told a story here, how would that story start?" Thus, the summarization prompt: "My second grader asked me what this passage means: …" When a given prompt isn't working and GPT-3 keeps pivoting into other modes of completion, that may mean that one hasn't constrained it enough by imitating a correct output, and one needs to go further; writing the first few words or sentence of the target output may be necessary.
Apple pioneered the voice revolution in 2011 with the introduction of Siri in its iPhone 4s. Today, you tell your iPhone 11, "Hey Siri, Play Bruce Springsteen by Spotify," and it responds, "I can't talk to Spotify, but you can use Apple music instead," politely displaying options on the screena as shown in the figure here. Or, you tell one of your five Amazon Echo devices at home, "Alexa, add pumpkin pie to my Target shopping list,"b then "order AA Duracell batteries," and it adds pumpkin pie and Amazon Basics batteries to your Amazon shopping cart, ignoring your request to shop at Target and be loyal to Duracell. You are the consumer, but your choices have been ignored. Or, consider you are a brand manager.
In most real-world applications, it is seldom the case that a given observable evolves independently of its environment. In social networks, users' behavior results from the people they interact with, news in their feed, or trending topics. In natural language, the meaning of phrases emerges from the combination of words. In general medicine, a diagnosis is established on the basis of the interaction of symptoms. Here, we propose a new model, the Interactive Mixed Membership Stochastic Block Model (IMMSBM), which investigates the role of interactions between entities (hashtags, words, memes, etc.) and quantifies their importance within the aforementioned corpora. We find that interactions play an important role in those corpora. In inference tasks, taking them into account leads to average relative changes with respect to non-interactive models of up to 150\% in the probability of an outcome. Furthermore, their role greatly improves the predictive power of the model. Our findings suggest that neglecting interactions when modeling real-world phenomena might lead to incorrect conclusions being drawn.
Katy Perry is sharing everything with her fans. The 32-year-old singer opened up about past suicidal thoughts during a live streamed therapy session to promote her new album, Witness, on Friday. WATCH: Katy Perry Previews New Album'Witness,' Goes Live on YouTube in'Big Brother'-Style House During a meeting with Siri Sat Nam Singh, a licensed therapist who appears on Viceland's The Therapist, Perry revealed that her 2013 song, "By the Grace of God," was inspired by her former thoughts of suicide. "I feel ashamed that I would have those thoughts, feel that low and that depressed," she said, adding that the song was written "because I do believe in something much bigger than me and I call that god for me." "You can be right or you can be loved," she added.
Michael Angelakos, the frontman of Passion Pit, is launching a company to support musicians and provide them with legal, educational and healthcare services, Mashable has learned. The New York City-based company, called The Wishart Group, has raised $250 million in funding, with contributions from big names in the music and tech industries. Angelakos, who declined to comment, is expected to publicly announce the project as early as this week. SEE ALSO: Starting Sunday, you can stream Prince's music almost everywhere The board, still growing, is comprised of tech leaders in various fields, including music distribution platforms and the artificial intelligence community. The project is being described as an "Artist Research and Protection Service" and is primarily focused on a mental health program.