Human use language not just to convey information but also to express their inner feelings and mental states. In this work, we adapt the state-of-the-art language generation models to generate affective (emotional) text. We posit a model capable of generating affect-driven and topic focused sentences without losing grammatical correctness as the affect intensity increases. We propose to incorporate emotion as prior for the probabilistic state-of-the-art text generation model such as GPT-2. The model gives a user the flexibility to control the category and intensity of emotion as well as the topic of the generated text. Previous attempts at modelling fine-grained emotions fall out on grammatical correctness at extreme intensities, but our model is resilient to this and delivers robust results at all intensities. We conduct automated evaluations and human studies to test the performance of our model, and provide a detailed comparison of the results with other models. In all evaluations, our model outperforms existing affective text generation models.

One of the ways they're cutting the corner on the fact that they have less resources for doing the moderation is they're just straight up blocking some of these terms and hashtags, which works better,

The report makes recommendations on how the arms control community could build on existing responsible AI initiatives and export control and …

Using artificial intelligence and supercomputing to drastically shorten the time doctors and researchers spend diagnosing diseases and developing …

Recommendation systems underpin the serving of nearly all online content in the modern age. From Youtube and Netflix recommendations, to Facebook feeds and Google searches, these systems are designed to filter content to the predicted preferences of users. Recently, these systems have faced growing criticism with respect to their impact on content diversity, social polarization, and the health of public discourse. In this work we simulate the recommendations given by collaborative filtering algorithms on users in the MovieLens data set. We find that prolonged exposure to system-generated recommendations substantially decreases content diversity, moving individual users into "echo-chambers" characterized by a narrow range of content. Furthermore, our work suggests that once these echo-chambers have been established, it is difficult for an individual user to break out by manipulating solely their own rating vector.

A number of exciting advances have been made in automated fact-checking thanks to increasingly larger datasets and more powerful systems, leading to improvements in the complexity of claims which can be accurately fact-checked. However, despite these advances, there are still desirable functionalities missing from the fact-checking pipeline. In this survey, we focus on the explanation functionality -- that is fact-checking systems providing reasons for their predictions. We summarize existing methods for explaining the predictions of fact-checking systems and we explore trends in this topic. Further, we consider what makes for good explanations in this specific domain through a comparative analysis of existing fact-checking explanations against some desirable properties. Finally, we propose further research directions for generating fact-checking explanations, and describe how these may lead to improvements in the research area.

This paper proposes a novel neural model for the understudied task of generating text from keywords. The model takes as input a set of un-ordered keywords, and part-of-speech (POS) based template instructions. This makes it ideal for surface realization in any NLG setup. The framework is based on the encode-attend-decode paradigm, where keywords and templates are encoded first, and the decoder judiciously attends over the contexts derived from the encoded keywords and templates to generate the sentences. Training exploits weak supervision, as the model trains on a large amount of labeled data with keywords and POS based templates prepared through completely automatic means. Qualitative and quantitative performance analyses on publicly available test-data in various domains reveal our system's superiority over baselines, built using state-of-the-art neural machine translation and controllable transfer techniques. Our approach is indifferent to the order of input keywords.

The success of deep learning is due, to a large extent, to the remarkable effectiveness of gradient-based optimization methods applied to large neural networks. In this talk I will discuss some general mathematical principles allowing for efficient optimization in over-parameterized non-linear systems, a setting that includes deep neural networks. Remarkably, it seems that optimization of such systems is "easy". In particular, optimization problems corresponding to these systems are not convex, even locally,but instead satisfy locally the Polyak-Lojasiewicz (PL) condition allowing for efficient optimization by gradient descent or SGD. We connect the PL condition of these systems to the condition number associated to the tangent kernel and develop a non-linear theory parallel to classical analyses of over-parameterized linear equations.

Machine learning has emerged to solve this, but many machine learning methods were typically limited to building an accurate prediction model as a " …

Every time Netflix recommends a new binge-worthy show for you, or Amazon suggests a related product, or Google helps you find the name of that one actor that was on the tip of your tongue, you're experiencing machine learning at work. All of these real-world applications use a subset of artificial intelligence technology to find patterns, solve problems, and accomplish tasks. But although machine learning, deep learning, and artificial intelligence (AI) are related, the differences between them can be confusing. In this post, we'll break down the differences in these exciting technologies in plain language, and explore how they're relevant to your business. Let's start with some definitions: Artificial intelligence is the study of how to build programs that can solve problems in a similar way to humans; it's about replicating human problem-solving and intelligence in machines. When working to develop AI, scientists quickly realized that teaching an AI every single thing it needed to know to perform its intended function was a non-starter.