We've been long working on improving the user experience in UGC products with machine learning. Here are our ten key lessons of implementing recommendation systems in business to build a really good product. The global task of the recommendation system is to select a shortlist of content from a large catalog that is most suitable for a particular user. The content itself can be different -- from products in the online store and articles to banking services. FunCorp product team works with the most interesting kind of content -- we recommend memes.

With the recent advances of conversational recommendations, the recommender system is able to actively and dynamically elicit user preference via conversational interactions. To achieve this, the system periodically queries users' preference on attributes and collects their feedback. However, most existing conversational recommender systems only enable the user to provide absolute feedback to the attributes. In practice, the absolute feedback is usually limited, as the users tend to provide biased feedback when expressing the preference. Instead, the user is often more inclined to express comparative preferences, since user preferences are inherently relative. To enable users to provide comparative preferences during conversational interactions, we propose a novel comparison-based conversational recommender system. The relative feedback, though more practical, is not easy to be incorporated since its feedback scale is always mismatched with users' absolute preferences. With effectively collecting and understanding the relative feedback from an interactive manner, we further propose a new bandit algorithm, which we call RelativeConUCB. The experiments on both synthetic and real-world datasets validate the advantage of our proposed method, compared to the existing bandit algorithms in the conversational recommender systems.

Over the past decades, researchers had put lots of effort investigating ranking techniques used to rank query results retrieved during information retrieval, or to rank the recommended products in recommender systems. In this project, we aim to investigate searching, ranking, as well as recommendation techniques to help to realize a university academia searching platform. Unlike the usual information retrieval scenarios where lots of ground truth ranking data is present, in our case, we have only limited ground truth knowledge regarding the academia ranking. For instance, given some search queries, we only know a few researchers who are highly relevant and thus should be ranked at the top, and for some other search queries, we have no knowledge about which researcher should be ranked at the top at all. The limited amount of ground truth data makes some of the conventional ranking techniques and evaluation metrics become infeasible, and this is a huge challenge we faced during this project. This project enhances the user's academia searching experience to a large extent, it helps to achieve an academic searching platform which includes researchers, publications and fields of study information, which will be beneficial not only to the university faculties but also to students' research experiences.

Ironically, the impact on jobs – although widely uncertain – is the part that people professionals are probably already well placed to handle. They will be all too familiar with changes to staffing requirements caused by global shocks, new products and opportunities, or the behaviour of competitors. They will therefore find they can deal with the most talked about bit of AI – the robo-apocalypse on jobs – in their stride. There are, however, a host of other, less well-discussed, challenges that business leaders will need to think about in order to harness the potential that artificial intelligence has to make organisations more efficient and more effective. Artificial intelligence (AI) is an umbrella term for a suite of technologies that performs tasks usually associated with human intelligence.

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.