Waterdrop Inc. ("Waterdrop", the "Company" or "we") (NYSE: WDH), a leading technology platform dedicated to insurance and healthcare service with a positive social impact, recently announced that it officially launched its first digital employee "Waterdrop Assistant". "Waterdrop Assistant" is a human-like virtual employee that was developed based on Waterdrop's business processes and is powered by multiple technologies, including robotic process automation (RPA) and artificial intelligence (AI). "Waterdrop Assistant" can help the online insurance service team with numerous tasks, including data processing and analysis, online user management, and customer services, thus improving the response time, quality, and scope of the Company's customer service team. Mr. Mingxing Huang, Head of AI at Waterdrop, commented, "The introduction of digital employees is our latest exploration to continue promoting the digital transformation of the insurance industry, to reduce operating costs, and improve the efficiency of insurance services. Specifically in our case, 'Waterdrop Assistant' has helped shorten the response time, lower operating costs, and unleash the potential of our staff. Our analysis shows that since its launch, 'Waterdrop Assistant' has processed 86% of the user sessions with a 97% accuracy rate for intention recognition, helping free up 37% of the customer service manpower and effectively increase the policy renewal rate. Currently, 'Waterdrop Assistant' is responsible for highly repetitive and labor-intensive tasks, however, it has also undergone constant system iterations and architecture upgrades through ongoing machine learning. For example, in the fourth quarter of 2021, Waterdrop Assistant completed 20-plus system iterations and 3 architecture upgrades accumulatively. Our next goal is to enable'Waterdrop Assistant' to independently complete tasks for more complex and interactive scenarios and play a bigger role in the process of sales inquiry, underwriting review, risk control, and claim settlement."

Natural language processing (NLP) enables an intuitive form of communication between humans and intelligent systems using human languages. NLP drives modern interactive voice response (IVR) systems by processing language to improve communication. Chatbots are the most common application of NLP in business. Advanced virtual assistants, sometimes called conversational AI agents, are powered by conversational user interfaces, NLP, and semantic and deep learning techniques. Progressing beyond chatbots, advanced virtual assistants listen to and observe behaviors, build and maintain data models, and predict and recommend actions to assist people with and automate tasks that were previously only possible for humans to accomplish.

Popularity bias is the idea that a recommender system will unduly favor popular artists when recommending artists to users. As such, they may contribute to a winner-take-all marketplace in which a small number of artists receive nearly all of the attention, while similarly meritorious artists are unlikely to be discovered. In this paper, we attempt to measure popularity bias in three state-of-art recommender system models (e.g., SLIM, Multi-VAE, WRMF) and on three commercial music streaming services (Spotify, Amazon Music, YouTube). We find that the most accurate model (SLIM) also has the most popularity bias while less accurate models have less popularity bias. We also find no evidence of popularity bias in the commercial recommendations based on a simulated user experiment.

Intent detection is a key part of any Natural Language Understanding (NLU) system of a conversational assistant. Detecting the correct intent is essential yet difficult for email conversations where multiple directives and intents are present. In such settings, conversation context can become a key disambiguating factor for detecting the user's request from the assistant. One prominent way of incorporating context is modeling past conversation history like task-oriented dialogue models. However, the nature of email conversations (long form) restricts direct usage of the latest advances in task-oriented dialogue models. So in this paper, we provide an effective transfer learning framework (EMToD) that allows the latest development in dialogue models to be adapted for long-form conversations. We show that the proposed EMToD framework improves intent detection performance over pre-trained language models by 45% and over pre-trained dialogue models by 30% for task-oriented email conversations. Additionally, the modular nature of the proposed framework allows plug-and-play for any future developments in both pre-trained language and task-oriented dialogue models.

In 2002, I waited more than ten minutes to download a single song using a 56k dial-up modem. Audio cassettes were still very much in vogue. Fast forward to 2022, and one can now instruct their phone or car to play their favorite tracks using their voice. We can sign into our favorite music streaming service automatically, and it shows us the music and artists that may fit depending on the mood, the time or the occasion. One can automate nearly all electrical systems in their house to operate on their schedule (remind them to get groceries, switch on lights when they enter, etc.).

In the PaLM-SayCan project, Google is combining current robotics technology with advances in large language models. Advances in large-scale AI language models have so far mainly arrived in our digital lives, such as text translation, text and image generation, or behind the scenes, when tech platforms use language AI to moderate the content. In the PaLM-SayCan project, various Google divisions are now combining the company's most advanced large-scale speech model to date with an everyday robot that could one day help in the home – an assistant for the real world. But that will take a while yet. Google unveiled the giant AI language model PaLM in early April, crediting the model with "breakthrough capabilities" in language understanding and, specifically, reasoning. PaLM stands for "Pathways Language Model" – making it a building block in Google's grand Pathways AI strategy for next-generation AI that can efficiently handle thousands or millions of tasks.

Google CEO Sundar Pichai has described the advent of artificial intelligence (AI) as more revolutionary than the discovery of fire or electricity. According to PwC, it has the potential to contribute $15 trillion to the global industry by 2030. I have worked with countless organizations on their AI strategies; however, companies wanting to capitalize on AI face significant barriers regarding the skills and resources needed to put it to use. To bridge this gap, many businesses turn to AI consultancies. These experts have the specialized knowledge and experience required to help companies deploy AI to create more intelligent products and services, improve their internal processes, and ultimately make better use of the data available to them. One of the most frequently asked questions I get from clients is: can you recommend an AI consulting firm to help us turn our AI ambitions into practice?

All beloved by the gay community way before they went mainstream. Similarly, no celebration of a decade of dating apps would be complete without acknowledging that the LGBTQ community ran to a different calendar there, too. The daddy of our contributions to now-ubiquitous swipe culture is the infamous Grindr, launched in 2009 and originally designed to coordinate hookups between likeminded gentlemen tired of chatting on glitchy websites or over discounted cocktails in samey bars. Grindr's runaway success wasn't just down to cutting out various dating-world middlemen, it also fulfilled a genuine need for the LGBTQ community. Marginalised people have always found sanctuary on the internet, scurrying to secluded corners to be better understood by those who shared their distinctive struggles, kinks or slightly nerdy hobbies; all things that might be mocked by the more conventionally attractive bantersauruses roaming our school corridors and haunting the chain pubs on our high streets.

Apple's Machine Learning and AI team transform every Apple product and because we fully integrate hardware and software, we can collaborate to deliver amazing experiences while protecting user data. The Machine Learning Platform and Technology Team is building and improving the on device inference stack. We are looking for a driven and dedicated ML Software Performance Engineer. In this role, you will work with a team to analyze the behavior of current models and products and also directly implement changes to the inference stack. The work that we do is a vital component of how users and developers experience ML on Apple's products. Join this group, and you'll have a direct impact on the performance of ML across Apple's products. C/C or similar languages with willingness to learn.

Automated recommendations can nowadays be found on many e-commerce platforms, and such recommendations can create substantial value for consumers and providers. Often, however, not all recommendable items have the same profit margin, and providers might thus be tempted to promote items that maximize their profit. In the short run, consumers might accept non-optimal recommendations, but they may lose their trust in the long run. Ultimately, this leads to the problem of designing balanced recommendation strategies, which consider both consumer and provider value and lead to sustained business success. This work proposes a simulation framework based on agent-based modeling designed to help providers explore longitudinal dynamics of different recommendation strategies. In our model, consumer agents receive recommendations from providers, and the perceived quality of the recommendations influences the consumers' trust over time. We design several recommendation strategies which either give more weight on provider profit or on consumer utility. Our simulations show that a hybrid strategy that puts more weight on consumer utility but without ignoring profitability considerations leads to the highest cumulative profit in the long run. This hybrid strategy results in a profit increase of about 20 % compared to pure consumer or profit oriented strategies. We also find that social media can reinforce the observed phenomena. In case when consumers heavily rely on social media, the cumulative profit of the best strategy further increases. To ensure reproducibility and foster future research, we publicly share our flexible simulation framework.