We propose a novel reinforcement learning based framework PoBRL for solving multi-document summarization. PoBRL jointly optimizes over the following three objectives necessary for a high-quality summary: importance, relevance, and length. Our strategy decouples this multi-objective optimization into different subproblems that can be solved individually by reinforcement learning. Utilizing PoBRL, we then blend each learned policies together to produce a summary that is a concise and complete representation of the original input. Our empirical analysis shows state-of-the-art performance on several multi-document datasets. Human evaluation also shows that our method produces high-quality output.

In many public health settings, it is important for patients to adhere to health programs, such as taking medications and periodic health checks. Unfortunately, beneficiaries may gradually disengage from such programs, which is detrimental to their health. A concrete example of gradual disengagement has been observed by an organization that carries out a free automated call-based program for spreading preventive care information among pregnant women. Many women stop picking up calls after being enrolled for a few months. To avoid such disengagements, it is important to provide timely interventions. Such interventions are often expensive and can be provided to only a small fraction of the beneficiaries. We model this scenario as a restless multi-armed bandit (RMAB) problem, where each beneficiary is assumed to transition from one state to another depending on the intervention. Moreover, since the transition probabilities are unknown a priori, we propose a Whittle index based Q-Learning mechanism and show that it converges to the optimal solution. Our method improves over existing learning-based methods for RMABs on multiple benchmarks from literature and also on the maternal healthcare dataset.

Width-based search algorithms seek plans by prioritizing states according to a suitably defined measure of novelty, that maps states into a set of novelty categories. Space and time complexity to evaluate state novelty is known to be exponential on the cardinality of the set. We present novel methods to obtain polynomial approximations of novelty and width-based search. First, we approximate novelty computation via random sampling and Bloom filters, reducing the runtime and memory footprint. Second, we approximate the best-first search using an adaptive policy that decides whether to forgo the expansion of nodes in the open list. These two techniques are integrated into existing width-based algorithms, resulting in new planners that perform significantly better than other state-of-the-art planners over benchmarks from the International Planning Competitions.

Higher-order methods for dependency parsing can partially but not fully addresses the issue that edges in dependency tree should be constructed at the text span/subtree level rather than word level. % This shortcoming can cause an incorrect span covered the corresponding tree rooted at a certain word though the word is correctly linked to its head. In this paper, we propose a new method for dependency parsing to address this issue. The proposed method constructs dependency trees by directly modeling span-span (in other words, subtree-subtree) relations. It consists of two modules: the {\it text span proposal module} which proposes candidate text spans, each of which represents a subtree in the dependency tree denoted by (root, start, end); and the {\it span linking module}, which constructs links between proposed spans. We use the machine reading comprehension (MRC) framework as the backbone to formalize the span linking module in an MRC setup, where one span is used as a query to extract the text span/subtree it should be linked to. The proposed method comes with the following merits: (1) it addresses the fundamental problem that edges in a dependency tree should be constructed between subtrees; (2) the MRC framework allows the method to retrieve missing spans in the span proposal stage, which leads to higher recall for eligible spans. Extensive experiments on the PTB, CTB and Universal Dependencies (UD) benchmarks demonstrate the effectiveness of the proposed method. We are able to achieve new SOTA performances on PTB and UD benchmarks, and competitive performances to previous SOTA models on the CTB dataset. Code is available at https://github.com/ShannonAI/mrc-for-dependency-parsing.

Artificial Intelligence (AI) As a Service Market to 2025 – Updated with Impact of COVID-19 is latest research study released by Adroit Market Research evaluating the market, highlighting opportunities, risk side analysis, and leveraged with strategic and tactical decision-making support. The study provides information on market trends and development, drivers, capacities, technologies, and on the changing investment structure of the Artificial Intelligence (AI) As a Service Market to 2025 – Updated with Impact of COVID-19 Market. Adroit Market Research's "Artificial Intelligence (AI) As a Service Market to 2025 – Updated with Impact of COVID-19″ provides a comprehensive coverage on Artificial Intelligence (AI) As a Service industry. It provides historical and forecast data on the country's coal production, consumption, and imports. The production section provides an extensive analysis over the trend of production, impact of the COVID-19 and information on production by company, by type, by grade and by state.

This evening at a press event to kickoff MWC Barcelona, I had the pleasure of joining CEO Satya Nadella and Technical Fellow Alex Kipman onstage to talk in depth about Microsoft's worldview for the intelligent cloud and intelligent edge. As part of today's press event, we also introduced the world to HoloLens 2. This is a tremendously exciting time for Microsoft, our partners, our customers, the computing industry and indeed the world. The virtually limitless computing power and capability of the cloud combined with increasingly intelligent and perceptive edge devices embedded throughout the physical world create experiences we could only imagine a few short years ago. When intelligent cloud and intelligent edge experiences are infused with mixed reality, we have a framework for achieving amazing things and empowering even more people. Today represents an important milestone for Microsoft.

This story was originally published by Undark and is reproduced here as part of the Climate Desk collaboration. Early one winter morning in 2020, Kurt VerCauteren discovered a cluster of dead birds in a barren field in northwest Texas. They were small birds, mostly dark-eyed juncos, but also a smattering of white-crowned sparrows. VerCauteren's team had poisoned them, inadvertently. The clues were clear, the death uncomplicated: The birds had flown in before dawn to scavenge deadly morsels of a contaminated peanut paste, left behind after a sounder of wild hogs had torn through the area in a feeding frenzy. The birds likely died within minutes of eating. "I couldn't even see the crumbs," says VerCauteren, a wildlife biologist at the US Department of Agriculture in Fort Collins, Colorado, who has spent years developing and testing pig poisons. The birds were the unintended victims of a field experiment to test a toxicant--one intended for feral pigs, but no other animals--that had been developed in Australia.

Title: The AI-First Company: How to Compete and Win with Artificial Intelligence Author: Ash Fontana Published: 2021 by Portfolio / Penguin What It Teaches: Ash Fontana is a managing director of Zetta Venture Partners, an investment fund focused on AI. He draws upon the lessons he's learned through the companies he's invested in and worked with to share a very broad array of observations about how companies should think about, leverage, and manage data and artificial intelligence. He introduces a new concept, data learning effects, as the driving value creator in what I call the Connected Intelligence age. When To Use It: In the book's conclusion, Fontana describes the contents of The AI-First Company as "fresh data" that leaders can "process" and combine with other inputs as they iteratively create reinforcing learning loops that enable them to create their own competitive advantage. As such, the broad array of information in the book shouldn't be viewed as perfect or a step-by-step roadmap for building a winning AI-led strategy, but rather one input among others that can help inform your strategy, if appropriately filtered and evaluated.

The belief that AI dominance is imperative for economic development, military control, and strategic competitiveness has accelerated AI development initiatives across countries. The release of national strategic plans has been accompanied by billions of dollars in investment as well as concrete policies to attract relevant talent and technology. In our previous post "How different countries view artificial intelligence", we presented a snapshot of governments' planning for AI, based on our analysis of 34 national strategic AI plans. Our post covered the description of AI plans and categorized countries based on their coverage of various related concepts. In this post, we extend details about what accounts for the variation in countries' AI plans.

The minimum cost lifted multicut approach has proven practically good performance in a wide range of applications such as image decomposition, mesh segmentation, multiple object tracking, and motion segmentation. It addresses such problems in a graph-based model, where real-valued costs are assigned to the edges between entities such that the minimum cut decomposes the graph into an optimal number of segments. Driven by a probabilistic formulation of minimum cost multicuts, we provide a measure for the uncertainties of the decisions made during the optimization. We argue that access to such uncertainties is crucial for many practical applications and conduct an evaluation by means of sparsifications on three different, widely used datasets in the context of image decomposition (BSDS-500) and motion segmentation (DAVIS2016 and FBMS59) in terms of variation of information (VI) and Rand index (RI).