Conversational recommender systems (CRS) aim to recommend high-quality items to users through interactive conversations. Although several efforts have been made for CRS, two major issues still remain to be solved. First, the conversation data itself lacks of sufficient contextual information for accurately understanding users' preference. Second, there is a semantic gap between natural language expression and item-level user preference. To address these issues, we incorporate both word-oriented and entity-oriented knowledge graphs (KG) to enhance the data representations in CRSs, and adopt Mutual Information Maximization to align the word-level and entity-level semantic spaces. Based on the aligned semantic representations, we further develop a KG-enhanced recommender component for making accurate recommendations, and a KG-enhanced dialog component that can generate informative keywords or entities in the response text. Extensive experiments have demonstrated the effectiveness of our approach in yielding better performance on both recommendation and conversation tasks.

Messenger advertisements (ads) give direct and personal user experience yielding high conversion rates and sales. However, people are skeptical about ads and sometimes perceive them as spam, which eventually leads to a decrease in user satisfaction. Targeted advertising, which serves ads to individuals who may exhibit interest in a particular advertising message, is strongly required. The key to the success of precise user targeting lies in learning the accurate user and ad representation in the embedding space. Most of the previous studies have limited the representation learning in the Euclidean space, but recent studies have suggested hyperbolic manifold learning for the distinct projection of complex network properties emerging from real-world datasets such as social networks, recommender systems, and advertising. We propose a framework that can effectively learn the hierarchical structure in users and ads on the hyperbolic space, and extend to the Multi-Manifold Learning. Our method constructs multiple hyperbolic manifolds with learnable curvatures and maps the representation of user and ad to each manifold. The origin of each manifold is set as the centroid of each user cluster. The user preference for each ad is estimated using the distance between two entities in the hyperbolic space, and the final prediction is determined by aggregating the values calculated from the learned multiple manifolds. We evaluate our method on public benchmark datasets and a large-scale commercial messenger system LINE, and demonstrate its effectiveness through improved performance.

How often do you reflect on the ways technology changes your life as a marketer? I mean the sly, step-by-way manner in which new tech slides neatly into your existing stack and subtly reframes the game on you. These changes don't always alter your job in dramatic ways, but they eliminate the hassles and headaches. They may speed up your time to results, automate painful routines, and enable you to focus on what matters most. Very rarely, these technologies also let you do things you'd never considered possible. No incoming martech makes a better case for this sort of incremental innovation than artificial intelligence. While new AI products are surely on the horizon--self-driving cars are coming any day now, possibly, maybe--AI's most dramatic effect on your job today lies in adding new features across the tools that you're already using.

Those who want to outfit a room or two with smart displays can get a couple of Amazon's smaller Echo Shows for less at HSN. The online retailer has a bundle that includes one Echo Show 5 and one Echo Show 8 for $140, which is a great price and close to the sale prices we saw for both of those devices back in May. If you were to buy each smart speaker separately right now, you'd spend $170 -- and that's with both the Show 5 and the Show 8 technically being on sale. In May, Amazon dropped the prices of both smart speakers to their Black Friday lows. If you had purchased one of each then, you would have paid $130.

Scientists say online daters and singletons'might as well let a stranger pick their dates' because they don't really know what they want in a romantic partner. US researchers say they've found little evidence that people actually desire romantic partners who uniquely fit their ideal description or type. Singletons often become so romantically interested in prospective matches that they convince themselves that their date does possess the traits they deem most desirable. A person's ideal partner does not reflect'any unique personal insight' of tastes, researchers say – and when we say what we like in a partner we're actually just describing qualities that everyone likes. The research could help shift online dating away from a model that focuses on stringently matching profiles and attributes.

Amazon's Summer Sale 2020 is here! The sale, which ends on Sunday, July 12, is a great time to pick up incredible bargains across Amazon's departments, including big savings on popular tech items. From top-rated fitness trackers and smart bathroom scales to bestselling wireless headphones, there are several deals on Amazon you need to know about. This includes an unmissable saving on Amazon's Echo Plus (2nd Gen). You can now get the Alexa smart speaker with a huge 50 per cent off- that's a massive saving of £70.

The next challenge was to decide what to sell beyond books. They picked CDs and DVDs. Over the years, electronics, toys and clothing followed, as did overseas expansion. And all this time, Amazon was building a battalion of data-mining experts. Artificial intelligence expert Andreas Weigend was one of the first. Before joining, he had published more than 100 scientific articles, co-founded one of the first music recommendation systems, and worked on an application to analyse online trades in real-time.

With companies struggling to survive the COVID-19 storm, new approaches and tactics have replaced existing business models and strategies. However, the biggest challenge for businesses remain ensuring superior customer experience and preserving relationships to thrive in this new normal. In fact, according to a survey conducted by Forrester, consumers now feel more fragmented, disconnected and less trustworthy of brands than before. Accompanied with minimal physical interactions, companies are in search of devising unique ways to interact with customers and keep them happy and connected. Current customer service models are hinged on availability of an army of agents to satisfactorily resolve customer queries.

Artificial Intelligence is no longer a distant utopia. Many things have happened since John McCarthy coined the term at the 1956 Dartmouth Conference. What was once just a dream is now a reality – smart virtual assistants, chatbots, smart home devices, self-driving cars, drones, and other intelligent systems have become commonplace. AI technologies are now all around us, shaping every aspect of our lives and changing the world in the process. It's a booming domain that brings us one step closer to the world of tomorrow. It's obvious that AI has had a tremendous impact on all industries in recent years.

Latent user representations are widely adopted in the tech industry for powering personalized recommender systems. Most prior work infers a single high dimensional embedding to represent a user, which is a good starting point but falls short in delivering a full understanding of the user's interests. In this work, we introduce PinnerSage, an end-to-end recommender system that represents each user via multi-modal embeddings and leverages this rich representation of users to provides high quality personalized recommendations. PinnerSage achieves this by clustering users' actions into conceptually coherent clusters with the help of a hierarchical clustering method (Ward) and summarizes the clusters via representative pins (Medoids) for efficiency and interpretability. PinnerSage is deployed in production at Pinterest and we outline the several design decisions that makes it run seamlessly at a very large scale. We conduct several offline and online A/B experiments to show that our method significantly outperforms single embedding methods.