In vision-and-language grounding problems, fine-grained representations of the image are considered to be of paramount importance. Most of the current systems incorporate visual features and textual concepts as a sketch of an image. However, plainly inferred representations are usually undesirable in that they are composed of separate components, the relations of which are elusive. In this work, we aim at representing an image with a set of integrated visual regions and corresponding textual concepts, reflecting certain semantics. To this end, we build the Mutual Iterative Attention (MIA) module, which integrates correlated visual features and textual concepts, respectively, by aligning the two modalities.
Many web sites collect reviews of products and services and use them provide rankings of their quality. However, such rankings are not personalized. We investigate how the information in the reviews written by a particular user can be used to personalize the ranking she is shown. We propose a new technique, topic profile collaborative filtering, where we build user profiles from users' review texts and use these profiles to filter other review texts with the eyes of this user. We verify on data from an actual review site that review texts and topic profiles indeed correlate with ratings, and show that topic profile collaborative filtering provides both a better mean average error when predicting ratings and a better approximation of user preference orders.
Our ability to access, process, and analyze large quantities of data has been increasing at a dizzying pace over the last few years. This data-driven revolution is fundamentally changing many professional and academic fields. Many people, especially the long-term practitioners in humanities and similar disciplines, find this change worrying, and in many ways exactly contrary to the spirit of these disciplines. Pouring over long and demanding texts, while internalizing them and becoming personally immersed in them, seems to be at the very core of what these disciplines are all about. And yet, as both a lover of humanities and a die-hard techy, I find this latest development incredibly exciting.
AI is a technology that has been around for a long time already and has opened up many different avenues in the business world. However, despite the benefits, a recent Gartner study found that many organisations remain reluctant to apply AI, particularly in HR. In fact, only 17% of organisations are using AI-based solutions in their HR function. While the study suggests this trend will rise, with an additional 30% of organisations exploring AI in HR by 2022, it's clear that HR remains behind on the use of this technology, missing out on the key benefits that AI can bring, not only to the department operations but also to their employees and the wider business too. Choosing an AI-based solution for your organisation can be tough, especially when it is unclear how the technology can truly impact the business or what is required for the solution to be as effective as possible.
Watch out, ghostwriters: Artificial intelligence (AI) is coming for you. In a paper accepted at the NeurIPS 2018 conference in Montreal ("Content preserving text generation with attribute controls"), data scientists from the University of Michigan and Google Brain describe a machine learning architecture that's capable of not only generating sentences from a given sample, but changing the mood, complexity, tense, or even voice of the original text while preserving its meaning. This might one day be used for paraphrasing, the team posits, or machine translation and conversational systems. And it could complement systems like those demonstrated by Microsoft Research in November, which leverage sophisticated natural language processing techniques to reason about relationships in weakly structured text. "In this work, we address the problem of modifying textual attributes of sentences," the researchers wrote.