We present graph-based translation models which translate source graphs into target strings. Source graphs are constructed from dependency trees with extra links so that non-syntactic phrases are connected. Inspired by phrase-based models, we first introduce a translation model which segments a graph into a sequence of disjoint subgraphs and generates a translation by combining subgraph translations left-to-right using beam search. However, similar to phrase-based models, this model is weak at phrase reordering. Therefore, we further introduce a model based on a synchronous node replacement grammar which learns recursive translation rules. We provide two implementations of the model with different restrictions so that source graphs can be parsed efficiently. Experiments on Chinese--English and German--English show that our graph-based models are significantly better than corresponding sequence- and tree-based baselines.

Playwright and screenwriter Tom Stoppard is perhaps best known for his postmodern Shakespearanisms--Rosencrantz and Guildenstern Are Dead and Shakespeare In Love (though I'd personally argue that his greatest works were Travesties and Brazil). But a new Stoppard biography from Hermione Lee has brought some new and revitalized attention to one of Stoppard's lesser-known literary contributions:… READ THE REST

A Lawrence Livermore National Laboratory team has developed a new deep reinforcement learning framework for a type of discrete optimization called symbolic regression, showing it could outperform several common methods, including commercial software gold standards, on benchmark problems. The work is being featured at the upcoming International Conference on Learning Representations. From left: LLNL team members Brenden Petersen, Mikel Landajuela, Nathan Mudhenk, Soo Kim, Ruben Glatt and Joanne Kim. Lawrence Livermore National Laboratory (LLNL) computer scientists have developed a new framework and an accompanying visualization tool that leverages deep reinforcement learning for symbolic regression problems, outperforming baseline methods on benchmark problems. The paper was recently accepted as an oral presentation at the International Conference on Learning Representations (ICLR 2021), one of the top machine learning conferences in the world.

The main goal in task planning is to build a sequence of actions that takes an agent from an initial state to a goal state. In robotics, this is particularly difficult because actions usually have several possible results, and sensors are prone to produce measurements with error. Partially observable Markov decision processes (POMDPs) are commonly employed, thanks to their capacity to model the uncertainty of actions that modify and monitor the state of a system. However, since solving a POMDP is computationally expensive, their usage becomes prohibitive for most robotic applications. In this paper, we propose a task planning architecture for service robotics. In the context of service robot design, we present a scheme to encode knowledge about the robot and its environment, that promotes the modularity and reuse of information. Also, we introduce a new recursive definition of a POMDP that enables our architecture to autonomously build a hierarchy of POMDPs, so that it can be used to generate and execute plans that solve the task at hand. Experimental results show that, in comparison to baseline methods, by following a recursive hierarchical approach the architecture is able to significantly reduce the planning time, while maintaining (or even improving) the robustness under several scenarios that vary in uncertainty and size.

In her first major speech to a U.S. audience after the U.S. presidential election, European Commission President Ursula von der Leyen laid out priority areas for transatlantic cooperation. She proposed building a new relationship between Europe and the United States, one that would encompass transatlantic coordination on digital technology issues, including working together on global standards for regulating artificial intelligence (AI) aligned with EU values. A reference to cooperation on standards for AI was included in the New Transatlantic Agenda for Global Change issued by the Commission on December 2, 2020. In remarks to Parliament on January 22, 2021, President von der Leyen called for "creating a digital economy rule book" with the United States that is "valid worldwide." Some would say Europe's new outreach on issues of tech governance and the suggestion of establishing an "EU-U.S. Trade and Technology Council" is incongruous to the current regulatory war being waged against ...

For those engaged in advocacy around the social harms of AI systems, a definitional exercise could, however, be a key way to rescue AI from the abstract, and foreground social and material concerns around these systems. Just as glossy data visualizations can obscure the unequal impacts and governance failures of the pandemic, AI as an abstract buzzword can be brandished against complex social problems as if it were a neutral and external'solution' rather than a sociotechnical system 14 designed and developed to make value-laden choices and trade-offs.

This paper presents a method to identify substructures in NMR spectra of mixtures, specifically 2D spectra, using a bespoke image-based Convolutional Neural Network application. This is done using HSQC and HMBC spectra separately and in combination. The application can reliably detect substructures in pure compounds, using a simple network. It can work for mixtures when trained on pure compounds only. HMBC data and the combination of HMBC and HSQC show better results than HSQC alone.

Domain generalization is a sub-field of transfer learning that aims at bridging the gap between two different domains in the absence of any knowledge about the target domain. Our approach tackles the problem of a model's weak generalization when it is trained on a single source domain. From this perspective, we build an ensemble model on top of base deep learning models trained on a single source to enhance the generalization of their collective prediction. The results achieved thus far have demonstrated promising improvements of the ensemble over any of its base learners.

The SingularityU Miami Chapter wraps its three-part online/Zoom artificial intelligence series with two seasoned experts (Philip Evens, Senior Advisor and Fellow at Boston Consulting Group) and Roy Lawrance (Founder and CEO of Applied Data Science, LLC). Both prescribe to a presbyopic technological world view and will candidly share their professional experience and best practices and applications about business and artificial intelligence. Please join us and come with lots of curiosity and questions! Philip Evans is the author of "Blown to Bits: How the New Economics of Information Transforms Strategy." In his book, Evans (and co-author Thomas Wurster) argue that with the spread of connectivity and common standards, your customers will increasingly have rich access to a universe of alternatives, your suppliers will exploit direct access to your customers, and focused competitors will pick off the most profitable parts of your value chain.

This ongoing work attempts to understand and address the requirements of UNICEF, a leading organization working in children's welfare, where they aim to tackle the problem of air quality for children at a global level. We are motivated by the lack of a proper model to account for heavily fluctuating air quality levels across the world in the wake of the COVID-19 pandemic, leading to uncertainty among public health professionals on the exact levels of children's exposure to air pollutants. We create an initial model as per the agency's requirement to generate insights through a combination of virtual meetups and online presentations. Our research team comprised of UNICEF's researchers and a group of volunteer data scientists. The presentations were delivered to a number of scientists and domain experts from UNICEF and community champions working with open data. We highlight their feedback and possible avenues to develop this research further.