Media
Interesting, But Less Spoken Facts about Artificial Intelligence
We all know how artificial intelligence has solidified its presence in many spheres of human activity. The technology has been receiving a huge amount of recognition from industry players, investors, and businesses who initiated to equip their machines with intelligence, deploy automation and employ robots to do carry out works. Even though the applications of artificial intelligence are out in the light, a lot of facts about the technology are still kept in the shadow. Analytics Insight unravels some interesting facts about artificial intelligence that are less spoken. Even though the tech space is lacking women employees, it is noted that most of the AI bots are female.
Making music from spider webs
Spiders are master builders, expertly weaving strands of silk into intricate 3D webs that serve as the spider's home and hunting ground. If humans could enter the spider's world, they could learn about web construction, arachnid behavior and more. Today, scientists report that they have translated the structure of a web into music, which could have applications ranging from better 3D printers to cross-species communication and otherworldly musical compositions. The researchers will present their results today at the spring meeting of the American Chemical Society (ACS). "The spider lives in an environment of vibrating strings," says Markus Buehler, Ph.D., the project's principal investigator, who is presenting the work.
Introduction to NLP Deep Learning Theories
Deep learning models rely on numerical vectors to'understand' the input words. We can think of the numerical vectors as high dimensional features representing the input words. In this high dimensional space, words are located close together or far away from each other. Word representation is built by finding the proper numerical vector representations for all the words in a given corpus. The quality of word representation relies on the corpus. This can be easily understood in the way that two human beings can have a different understanding of the same word, depending on whether he likes to spend time reading the modern newspaper or Shakespeare's literature. Besides, the quality of word representation heavily relies on the methods to find numerical vector representations for all the words. There are several methods to generate word representation by learning from the words' context.
Unified and Multilingual Author Profiling for Detecting Haters
Schlicht, Ipek Baris, de Paula, Angel Felipe Magnossão
This paper presents a unified user profiling framework to identify hate speech spreaders by processing their tweets regardless of the language. The framework encodes the tweets with sentence transformers and applies an attention mechanism to select important tweets for learning user profiles. Furthermore, the attention layer helps to explain why a user is a hate speech spreader by producing attention weights at both token and post level. Our proposed model outperformed the state-of-the-art multilingual transformer models.