Intelligent assistants like Cortana, Siri, Alexa, and Google Assistant are trained to parse information when the conversation is synchronous and short; however, for email-based conversational agents, the communication is asynchronous, and often contains information irrelevant to the assistant. This makes it harder for the system to accurately detect intents, extract entities relevant to those intents and thereby perform the desired action. We present a neural model for scoping relevant information for the agent from a large query. We show that when used as a preprocessing step, the model improves performance of both intent detection and entity extraction tasks. We demonstrate the model's impact on Scheduler (Cortana is the persona of the agent, while Scheduler is the name of the service. We use them interchangeably in the context of this paper.) - a virtual conversational meeting scheduling assistant that interacts asynchronously with users through email. The model helps the entity extraction and intent detection tasks requisite by Scheduler achieve an average gain of 35% in precision without any drop in recall. Additionally, we demonstrate that the same approach can be used for component level analysis in large documents, such as signature block identification.

Matrix factorization (MF) has been widely applied to collaborative filtering in recommendation systems. Its Bayesian variants can derive posterior distributions of user and item embeddings, and are more robust to sparse ratings. However, the Bayesian methods are restricted by their update rules for the posterior parameters due to the conjugacy of the priors and the likelihood. Neural networks can potentially address this issue by capturing complex mappings between the posterior parameters and the data. In this paper, we propose a variational auto-encoder based Bayesian MF framework. It leverages not only the data but also the information from the embeddings to approximate their joint posterior distribution. The approximation is an iterative procedure with cross feedback of user and item embeddings to the others' encoders. More specifically, user embeddings sampled in the previous iteration, alongside their ratings, are fed back into the item-side encoders to compute the posterior parameters for the item embeddings in the current iteration, and vice versa. The decoder network then reconstructs the data using the MF with the currently re-sampled user and item embeddings. We show the effectiveness of our framework in terms of reconstruction errors across five real-world datasets. We also perform ablation studies to illustrate the importance of the cross feedback component of our framework in lowering the reconstruction errors and accelerating the convergence.

The development of fair machine learning models that effectively avert bias and discrimination is an important problem that has garnered attention in recent years. The necessity of encoding complex relational dependencies among the features and variables for competent predictions require the development of fair, yet expressive relational models. In this work, we introduce Fair-A3SL, a fairness-aware structure learning algorithm for learning relational structures, which incorporates fairness measures while learning relational graphical model structures. Our approach is versatile in being able to encode a wide range of fairness metrics such as statistical parity difference, overestimation, equalized odds, and equal opportunity, including recently proposed relational fairness measures. While existing approaches employ the fairness measures on pre-determined model structures post prediction, Fair-A3SL directly learns the structure while optimizing for the fairness measures and hence is able to remove any structural bias in the model. We demonstrate the effectiveness of our learned model structures when compared with the state-of-the-art fairness models quantitatively and qualitatively on datasets representing three different modeling scenarios: i) a relational dataset, ii) a recidivism prediction dataset widely used in studying discrimination, and iii) a recommender systems dataset. Our results show that Fair-A3SL can learn fair, yet interpretable and expressive structures capable of making accurate predictions.

Online dating going mainstream hasn't made the potential dangers of meeting up with an internet stranger any less alarming. That's why Match.com is rolling out a check-in feature that lets users shoot over their date details to trusted confidantes, including the name of the person they're meeting up with, the location of the date and the time. Once check-in is turned on, users will receive an automated text message during their date asking them if everything is going alright and if they'd like to notify their previously listed emergency contacts if it's not. Match.com is letting users notify emergency contacts if their date is showing any red flags. Check-in sends users a text that users can reply to and send trusted contacts their date's name, the location of the date and the time The user can then reply'yes' to the text message and all three contacts will be notified.

Smart speakers, such as Amazon Echo, have been adopted by millions of users. However, the privacy impacts of smart speakers have not been well examined. We investigate the privacy leakage of smart speakers under an encrypted traffic analysis attack, referred to as voice command fingerprinting. In this attack, an adversary eavesdrops encrypted voice traffic from and to a smart speaker and infers which voice command a user says without decrypting encrypted traffic. We design our attacks based on neural networks and collect two large-scale datasets on Amazon Echo and Google Home by using an automatic traffic crawler.

If you go down to the farm today, you'll likely find it packed with sensors, drones and remote management systems run by iPhones, iPads and other mobile devices. In fact, we're only one or two Siri Shortcuts away from voice-controlled farms equipped with remotely controlled irrigation, livestock and crop management solutions and blockchain-based crop lifecycle analysis tools. Most of this technology exists, but cost constrains deployment. Leading the digital transformation of agriculture are apps, such as: Agrellus, an online marketplace for agriculture, xarvio Scouting App for better crop management, FieldNET Mobile to control water pivots remotely, Yara ImageIT, which turns your iPhone into a crop nutrient testing system, AgSense, and GrainTruckPlus. There are many more apps for agriculture available at the App Store – including Tudder, the "Tinder for farm animals."

Point-of-Interest (POI) recommendation is one of the most important location-based services helping people discover interesting venues or services. However, the extreme user-POI matrix sparsity and the varying spatio-temporal context pose challenges for POI systems, which affects the quality of POI recommendations. To this end, we propose a translation-based relation embedding for POI recommendation. Our approach encodes the temporal and geographic information, as well as semantic contents effectively in a low-dimensional relation space by using Knowledge Graph Embedding techniques. To further alleviate the issue of user-POI matrix sparsity, a combined matrix factorization framework is built on a user-POI graph to enhance the inference of dynamic personal interests by exploiting the side-information. Experiments on two real-world datasets demonstrate the effectiveness of our proposed model.

Recommender system is an essential component of web services to engage users. Popular recommender systems model user preferences and item properties using a large amount of crowdsourced user-item interaction data, e.g., rating scores; then top-$N$ items that match the best with a user's preference are recommended to the user. In this work, we show that an attacker can launch a data poisoning attack to a recommender system to make recommendations as the attacker desires via injecting fake users with carefully crafted user-item interaction data. Specifically, an attacker can trick a recommender system to recommend a target item to as many normal users as possible. We focus on matrix factorization based recommender systems because they have been widely deployed in industry. Given the number of fake users the attacker can inject, we formulate the crafting of rating scores for the fake users as an optimization problem. However, this optimization problem is challenging to solve as it is a non-convex integer programming problem. To address the challenge, we develop several techniques to approximately solve the optimization problem. For instance, we leverage influence function to select a subset of normal users who are influential to the recommendations and solve our formulated optimization problem based on these influential users. Our results show that our attacks are effective and outperform existing methods.

In today's business era, AI chatbots are redefining the way pharma companies interact and engage with their clients. These chatbots mimic human conversation via text or auditory means which is a huge opportunity for the pharma industry to have a one-to-one conversation with their customers, doctors, and patients. Apart from that, by using intelligent virtual assistants, pharmaceutical companies can build a strong relationship with doctors and patients by communicating with them and assisting them directly. The two main areas within this industry that will drastically benefit from developing a pharma chatbot are R&D and marketing. By developing a chatbot, a pharma company can have a virtual digital assistant to provide information to users on various topics, such as how to respond to inquiries on certain health conditions, a complex drug procedure, and the appropriate method of using a certain medical device.

An important problem in multiview representation learning is finding the optimal combination of views with respect to the specific task at hand. To this end, we introduce NAM: a Neural Attentive Multiview machine that learns multiview item representations and similarity by employing a novel attention mechanism. NAM harnesses multiple information sources and automatically quantifies their relevancy with respect to a supervised task. Finally, a very practical advantage of NAM is its robustness to the case of dataset with missing views. We demonstrate the effectiveness of NAM for the task of movies and app recommendations. Our evaluations indicate that NAM outperforms single view models as well as alternative multiview methods on item recommendations tasks, including cold-start scenarios.