Recent years have witnessed rapid growth in satellite-based approaches to quantifying aspects of land use, especially those monitoring the outcomes of sustainable development programs. Burke et al. reviewed this recent progress with a particular focus on machine-learning approaches and artificial intelligence methods. Drawing on examples mostly from Africa, they conclude that satellite-based methods enhance rather than replace ground-based data collection, and progress depends on a combined approach. Science , this issue p. [eabe8628][1] ### BACKGROUND Accurate and comprehensive measurements of a range of sustainable development outcomes are fundamental inputs into both research and policy. For instance, good measures are needed to monitor progress toward sustainability goals and evaluate interventions designed to improve development outcomes. Traditional approaches to measurement of many key outcomes rely on household surveys that are conducted infrequently in many parts of the world and are often of low accuracy. The paucity of ground data stands in contrast to the rapidly growing abundance and quality of satellite imagery. Multiple public and private sensors launched in recent years provide temporal, spatial, and spectral information on changes happening on Earth’s surface. Here we review a rapidly growing scientific literature that seeks to use this satellite imagery to measure and understand various outcomes related to sustainable development. We pay particular attention to recent approaches that use methods from artificial intelligence to extract information from images, as these methods typically outperform earlier approaches and enable new insights. Our focus is on settings and applications where humans themselves, or what they produce, are the outcome of interest and on where these outcomes are being measured using satellite imagery. ### ADVANCES We describe and synthesize the variety of approaches that have been used to extract information from satellite imagery, with particular attention given to recent machine learning–based approaches and settings in which training data are limited or noisy. We then quantitatively assess predictive performance of these approaches in the domains of smallholder agriculture, economic livelihoods, population, and informal settlements. We show that satellite-based performance in predicting these outcomes is reasonably strong and improving. Performance improvements have come through a combination of more numerous and accurate training data, more abundant and higher-quality imagery, and creative application of advances in computer vision to satellite inputs and sustainability outcomes. Further, our analyses suggest that reported model performance likely understates true performance in many settings, given the noisy data on which predictions are evaluated and the types of noise typically observed in sustainability applications. For multiple outcomes of interest, satellite-based estimates can now equal or exceed the accuracy of traditional approaches to outcome measurement. We describe multiple methods through which the true performance of satellite-based approaches can be better understood. Integration of satellite-based sustainability measurements into research has been broad, and we describe applications in agriculture, fisheries, health, and economics. Documented uses of these measurements in public-sector decision-making are rarer, which we attribute in part to the novelty of the approaches, their lack of interpretability, and the potential benefits to some policy-makers of not having certain outcomes be measured. ### OUTLOOK The largest constraint to satellite-based model performance is now training data rather than imagery. While imagery has become abundant, the scarcity and frequent unreliability of ground data make both training and validation of satellite-based models difficult. Expanding the quantity and quality of such data will quickly accelerate progress in this field. Other opportunities for advancement include improvements in model interpretability, fusion of satellites with other nontraditional data that provide complementary information, and more-rigorous evaluation of satellite-based approaches (relative to available alternatives) in the context of specific use cases. Nevertheless, despite the current and future promise of satellite-based approaches, we argue that these approaches will amplify rather than replace existing ground-based data collection efforts in most settings. Many outcomes of interest will likely never be accurately estimated with satellites; for outcomes where satellites do have predictive power, high-quality local training data can nearly always improve model performance. ![Figure][2] Increasing collection of satellite imagery can help measure livelihood outcomes in areas where ground data are sparse. (Left) Interval between nationally representative economic surveys over the past three decades shows long lags in many developing countries. (Middle) Recently added public and private satellites have broken the traditional trade-off between temporal and spatial resolution. (Right) Performance in measuring the presence of informal settlements, crop yields on smallholder agricultural plots, and village-level asset wealth. R 2, coefficient of determination. Accurate and comprehensive measurements of a range of sustainable development outcomes are fundamental inputs into both research and policy. We synthesize the growing literature that uses satellite imagery to understand these outcomes, with a focus on approaches that combine imagery with machine learning. We quantify the paucity of ground data on key human-related outcomes and the growing abundance and improving resolution (spatial, temporal, and spectral) of satellite imagery. We then review recent machine learning approaches to model-building in the context of scarce and noisy training data, highlighting how this noise often leads to incorrect assessment of model performance. We quantify recent model performance across multiple sustainable development domains, discuss research and policy applications, explore constraints to future progress, and highlight research directions for the field. [1]: /lookup/doi/10.1126/science.abe8628 [2]: pending:yes

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.

Governments, investors and business leaders need to adopt practical solutions that can be deployed across the world at scale. The arrival of 5G along with wider adoption of AI technology into the physical world will make it possible to substantially enhance the opportunities to scale cleaner energy generation technologies, enable efficiency gains in manufacturing, our homes, retail stores, offices and transportation that will enable substantial reductions in pollution. Policies that incentivise the accelerated development and deployment of Industry 4.0 solutions will require politicians and regulators to better understand the opportunities that 5G alongside AI will enable. The OECD published a paper "What works in Innovation Policy" and observed that "Policies ignoring or resisting the industrial transition have proven to be not just futile but result in an innovative disadvantage and weak economic performance." Entering the new year will allow us to develop and deploy solutions for the 2020s that make use of the next industrial revolution with 5G and AI to enable dramatic efficiency gains across all sectors of the economy and to enhance renewable energy generation. The emergence of India, China and others as industrial economic powers is occurring at a time when we now know the damage that such pollution causes and hence there is a need to work together, collaboratively to solve a global problem. Embracing technological change and enhancing its capabilities to deliver better living standards alongside sustainable development is the best option for those who really want to make an impact on climate change at scale in the 2020s and beyond. I wish to thank Henry Derwent, former advisor to Prime Minister Margaret Thatcher and former CEO of IETA for his efforts to promote technological innovation and scaled up financing with Green Bonds.

Direct decoding for task-oriented dialogue is known to suffer from the explaining-away effect, manifested in models that prefer short and generic responses. Here we argue for the use of Bayes' theorem to factorize the dialogue task into two models, the distribution of the context given the response, and the prior for the response itself. This approach, an instantiation of the noisy channel model, both mitigates the explaining-away effect and allows the principled incorporation of large pretrained models for the response prior. We present extensive experiments showing that a noisy channel model decodes better responses compared to direct decoding and that a two stage pretraining strategy, employing both open-domain and task-oriented dialogue data, improves over randomly initialized models.

From Word2Vec to GloVe, word embedding models have played key roles in the current state-of-the-art results achieved in Natural Language Processing. Designed to give significant and unique vectorized representations of words and entities, those models have proven to efficiently extract similarities and establish relationships reflecting semantic and contextual meaning among words and entities. African Languages, representing more than 31% of the worldwide spoken languages, have recently been subject to lots of research. However, to the best of our knowledge, there are currently very few to none word embedding models for those languages words and entities, and none for the languages under study in this paper. After describing Glove, Word2Vec, and Poincar\'e embeddings functionalities, we build Word2Vec and Poincar\'e word embedding models for Fon and Nobiin, which show promising results. We test the applicability of transfer learning between these models as a landmark for African Languages to jointly involve in mitigating the scarcity of their resources, and attempt to provide linguistic and social interpretations of our results. Our main contribution is to arouse more interest in creating word embedding models proper to African Languages, ready for use, and that can significantly improve the performances of Natural Language Processing downstream tasks on them. The official repository and implementation is at https://github.com/bonaventuredossou/afrivec

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.

One of the oldest and most popular approaches to automated planning is to encode the problem at hand into a propositional formula and use a Satisfiability (SAT) solver to find a solution. In all established SAT-based approaches for Hierarchical Task Network (HTN) planning, grounding the problem is necessary and oftentimes introduces a combinatorial blowup in terms of the number of actions and reductions to encode. Our contribution named Lilotane (Lifted Logic for Task Networks) eliminates this issue for Totally Ordered HTN planning by directly encoding the lifted representation of the problem at hand. We lazily instantiate the problem hierarchy layer by layer and use a novel SAT encoding which allows us to defer decisions regarding method arguments to the stage of SAT solving. We show the correctness of our encoding and compare it to the best performing prior SAT encoding in a worst-case analysis. Empirical evaluations confirm that Lilotane outperforms established SAT-based approaches, often by orders of magnitude, produces much smaller formulae on average, and compares favorably to other state-of-the-art HTN planners regarding robustness and plan quality. In the International Planning Competition (IPC) 2020, a preliminary version of Lilotane scored the second place. We expect these considerable improvements to SAT-based HTN planning to open up new perspectives for SAT-based approaches in related problem classes.

Google and other search engines feature the entity search by representing a knowledge card summarizing related facts about the user-supplied entity. However, the knowledge card is limited to certain entities that have a Wiki page or an entry in encyclopedias such as Freebase. The current encyclopedias are limited to highly popular entities, which are far fewer compared with the emerging entities. Despite the availability of knowledge about the emerging entities on the search results, yet there are no approaches to capture, abstract, summerize, fuse, and validate fragmented pieces of knowledge about them. Thus, in this paper, we develop approaches to capture two types of knowledge about the emerging entities from a corpus extended from top-n search snippets of a given emerging entity. The first kind of knowledge identifies the role(s) of the emerging entity as, e.g., who is s/he? The second kind captures the entities closely associated with the emerging entity. As the testbed, we considered a collection of 20 emerging entities and 20 popular entities as the ground truth. Our approach is an unsupervised approach based on text analysis and entity embeddings. Our experimental studies show promising results as the accuracy of more than $87\%$ for recognizing entities and $75\%$ for ranking them. Besides $87\%$ of the entailed types were recognizable. Our testbed and source code is available on Github https://github.com/sunnyUD/research_source_code.

Along with the development of modern computing technology and social sciences, both theoretical research and practical applications of social computing have been continuously extended. In particular with the boom of artificial intelligence (AI), social computing is significantly influenced by AI. However, the conventional technologies of AI have drawbacks in dealing with more complicated and dynamic problems. Such deficiency can be rectified by hybrid human-artificial intelligence (H-AI) which integrates both human intelligence and AI into one unity, forming a new enhanced intelligence. H-AI in dealing with social problems shows the advantages that AI can not surpass. This paper firstly introduces the concept of H-AI. AI is the intelligence in the transition stage of H-AI, so the latest research progresses of AI in social computing are reviewed. Secondly, it summarizes typical challenges faced by AI in social computing, and makes it possible to introduce H-AI to solve these challenges. Finally, the paper proposes a holistic framework of social computing combining with H-AI, which consists of four layers: object layer, base layer, analysis layer, and application layer. It represents H-AI has significant advantages over AI in solving social problems.

Multilingual models have demonstrated impressive cross-lingual transfer performance. However, test sets like XNLI are monolingual at the example level. In multilingual communities, it is common for polyglots to code-mix when conversing with each other. Inspired by this phenomenon, we present two strong black-box adversarial attacks (one word-level, one phrase-level) for multilingual models that push their ability to handle code-mixed sentences to the limit. The former uses bilingual dictionaries to propose perturbations and translations of the clean example for sense disambiguation. The latter directly aligns the clean example with its translations before extracting phrases as perturbations. Our phrase-level attack has a success rate of 89.75% against XLM-R-large, bringing its average accuracy of 79.85 down to 8.18 on XNLI. Finally, we propose an efficient adversarial training scheme that trains in the same number of steps as the original model and show that it improves model accuracy.