In this paper, we propose Tutoring bot, a generative chatbot trained on a large scale of tutor-student conversations for English-language learning. To mimic a human tutor's behavior in language education, the tutor bot leverages diverse educational instructions and grounds to each instruction as additional input context for the tutor response generation. As a single instruction generally involves multiple dialogue turns to give the student sufficient speaking practice, the tutor bot is required to monitor and capture when the current instruction should be kept or switched to the next instruction. For that, the tutor bot is learned to not only generate responses but also infer its teaching action and progress on the current conversation simultaneously by a multi-task learning scheme. Our Tutoring bot is deployed under a non-commercial use license at https://tutoringai.com.

Using online information discovery as a case study, in this position paper we discuss the need to design, develop, and deploy (conversational) agents that can -- non-intrusively -- guide children in their quest for online resources rather than simply finding resources for them. We argue that agents should "let children learn" and should be built to take on a teacher-facilitator function, allowing children to develop their technical and critical thinking abilities as they interact with varied technology in a broad range of use cases.

Generative AI is absolutely everywhere right now, so it's no surprise to see Spotify putting it to use in its latest feature, simply called "DJ." It's a new way to immediately start a personalized selection of music playing that combines Spotify's well-known personalization tools that you can find in playlists like Discover Weekly as well as the content that populates your home screen with some AI tricks. I got early access to DJ and have been playing with it for the last day to see how Spotify's latest take on personalized music works, but the feature is available as of today in beta for all premium subscribers in the US and Canada. While Spotify has loads of personalized playlists for users, I've found that the app lacks a simple way to tell it to just play some music you like. On Apple Music, for example, I can ask Siri to play music I like and it'll start a personalized radio station based on music I've played alongside some things it thinks I'll enjoy but haven't played before. It's a reliable way to jump right into my collection.

While providing low latency is a fundamental requirement in deploying recommendation services, achieving high resource utility is also crucial in cost-effectively maintaining the datacenter. Co-locating multiple workers of a model is an effective way to maximize query-level parallelism and server throughput, but the interference caused by concurrent workers at shared resources can prevent server queries from meeting its SLA. Hera utilizes the heterogeneous memory requirement of multi-tenant recommendation models to intelligently determine a productive set of co-located models and its resource allocation, providing fast response time while achieving high throughput. We show that Hera achieves an average 37.3% improvement in effective machine utilization, enabling 26% reduction in required servers, significantly improving upon the baseline recommedation inference server.

A Chicago man was arrested for allegedly holding a woman he met on a dating app against her will and beating her. An Illinois man was arrested for allegedly holding a woman he met on a dating app against her will and beating her. The victim may have also been sexually assaulted. The man had been holding the woman against her will in his mother's house since Sunday, Dolton police told FOX 32 Chicago. On Monday, the pair went to an Advanced Auto Parts store.

At its most basic, AI refers to the development of computer systems that can perform tasks that would typically require human intelligence, such as recognizing speech, making decisions, and solving problems. There are many different types of AI, including machine learning, deep learning, and natural language processing, all of which are used to create more advanced and sophisticated AI systems. One of the most well-known applications of AI is virtual personal assistants, such as Apple's Siri and Amazon's Alexa. These systems use natural language processing to understand and respond to voice commands, allowing users to control their smart homes, make phone calls, and access information with just their voice. Another key area of AI development is self-driving cars, which use a combination of computer vision, machine learning, and other technologies to navigate roads and avoid obstacles.

Personalization is key in digital marketing, and AI makes it easier for businesses to personalize their marketing efforts. AI algorithms can analyze customer data and provide insights into customer behavior and preferences. This information can then be used to create targeted and personalized campaigns that resonate with customers. Personalized marketing campaigns result in increased customer engagement, higher conversion rates, and improved customer loyalty. Chatbots are a popular use of AI in digital marketing.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. A man is accused of tying up a woman he met on a dating app and beating her in the basement of his mom's Illinois home, police said. The suspect – who has not been identified by police – was arrested in Riverdale on Monday and charges are pending, FOX 32 reported. Police said the suspect had been holding the woman there against her will since Sunday.

Open domain conversational agents can answer a broad range of targeted queries. However, the sequential nature of interaction with these systems makes knowledge exploration a lengthy task which burdens the user with asking a chain of well phrased questions. In this paper, we present a retrieval based system and associated dataset for predicting the next questions that the user might have. Such a system can proactively assist users in knowledge exploration leading to a more engaging dialog. The retrieval system is trained on a dataset which contains ~14K multi-turn information-seeking conversations with a valid follow-up question and a set of invalid candidates. The invalid candidates are generated to simulate various syntactic and semantic confounders such as paraphrases, partial entity match, irrelevant entity, and ASR errors. We use confounder specific techniques to simulate these negative examples on the OR-QuAC dataset and develop a dataset called the Follow-up Query Bank (FQ-Bank). Then, we train ranking models on FQ-Bank and present results comparing supervised and unsupervised approaches. The results suggest that we can retrieve the valid follow-ups by ranking them in higher positions compared to confounders, but further knowledge grounding can improve ranking performance.

In this big data era, it is hard for the current generation to find the right data from the huge amount of data contained within online platforms. In such a situation, there is a need for an information filtering system that might help them find the information they are looking for. In recent years, a research field has emerged known as recommender systems. Recommenders have become important as they have many real-life applications. This paper reviews the different techniques and developments of recommender systems in e-commerce, e-tourism, e-resources, e-government, e-learning, and e-library. By analyzing recent work on this topic, we will be able to provide a detailed overview of current developments and identify existing difficulties in recommendation systems. The final results give practitioners and researchers the necessary guidance and insights into the recommendation system and its application.