War in Europe, a momentous volcanic eruption and a surprise finding that could rewrite our understanding of reality – 2022 really has been a busy year for science, technology, health and environment news, and all that happened in just the first few months. From stunning space imagery to pig heart transplants, here are the New Scientist news editors' picks of the biggest scientific developments, discoveries and events of the year. Russia's invasion of Ukraine in February has sparked devastation across the country and affected many areas of life around the world, as both nations play a key role in the global supply chains for energy, food and more. It has also raised the spectre of nuclear weapons, with Russian president Vladimir Putin making not-so veiled threats about deploying his atomic arsenal. Thankfully, Armageddon has been avoided, but Russia's offensive has sparked discussion of a new kind of nuclear war, as Ukraine's nuclear power plants became a battleground this year.

The outburst of COVID-19 in late 2019 was the start of a health crisis that shook the world and took millions of lives in the ensuing years. Many governments and health officials failed to arrest the rapid circulation of infection in their communities. The long incubation period and the large proportion of asymptomatic cases made COVID-19 particularly elusive to track. However, wastewater monitoring soon became a promising data source in addition to conventional indicators such as confirmed daily cases, hospitalizations, and deaths. Despite the consensus on the effectiveness of wastewater viral load data, there is a lack of methodological approaches that leverage viral load to improve COVID-19 forecasting. This paper proposes using deep learning to automatically discover the relationship between daily confirmed cases and viral load data. We trained one Deep Temporal Convolutional Networks (DeepTCN) and one Temporal Fusion Transformer (TFT) model to build a global forecasting model. We supplement the daily confirmed cases with viral loads and other socio-economic factors as covariates to the models. Our results suggest that TFT outperforms DeepTCN and learns a better association between viral load and daily cases. We demonstrated that equipping the models with the viral load improves their forecasting performance significantly. Moreover, viral load is shown to be the second most predictive input, following the containment and health index. Our results reveal the feasibility of training a location-agnostic deep-learning model to capture the dynamics of infection diffusion when wastewater viral load data is provided.

Knowledge Distillation (KD) is a commonly used technique for improving the generalization of compact Pre-trained Language Models (PLMs) on downstream tasks. However, such methods impose the additional burden of training a separate teacher model for every new dataset. Alternatively, one may directly work on the improvement of the optimization procedure of the compact model toward better generalization. Recent works observe that the flatness of the local minimum correlates well with better generalization. In this work, we adapt Stochastic Weight Averaging (SWA), a method encouraging convergence to a flatter minimum, to fine-tuning PLMs. We conduct extensive experiments on various NLP tasks (text classification, question answering, and generation) and different model architectures and demonstrate that our adaptation improves the generalization without extra computation cost. Moreover, we observe that this simple optimization technique is able to outperform the state-of-the-art KD methods for compact models.

In computer-aided education and intelligent tutoring systems, knowledge tracing (KT) raises attention due to the development of data-driven learning methods, which aims to predict students' future performance given their past question response sequences to trace their knowledge states. However, current deep learning approaches only focus on enhancing prediction accuracy, but neglecting the discrimination imbalance of responses. That is, a considerable proportion of question responses are weak to discriminate students' knowledge states, but equally considered compared to other discriminative responses, thus hurting the ability of tracing students' personalized knowledge states. To tackle this issue, we propose DR4KT for Knowledge Tracing, which reweights the contribution of different responses according to their discrimination in training. For retaining high prediction accuracy on low discriminative responses after reweighting, DR4KT also introduces a discrimination-aware score fusion technique to make a proper combination between student knowledge mastery and the questions themselves. Comprehensive experimental results show that our DR4KT applied on four mainstream KT methods significantly improves their performance on three widely-used datasets.

Most recent studies on neural constituency parsing focus on encoder structures, while few developments are devoted to decoders. Previous research has demonstrated that probabilistic statistical methods based on syntactic rules are particularly effective in constituency parsing, whereas syntactic rules are not used during the training of neural models in prior work probably due to their enormous computation requirements. In this paper, we first implement a fast CKY decoding procedure harnessing GPU acceleration, based on which we further derive a syntactic rule-based (rule-constrained) CKY decoding. In the experiments, our method obtains 95.89 and 92.52 F1 on the datasets of PTB and CTB respectively, which shows significant improvements compared with previous approaches. Besides, our parser achieves strong and competitive cross-domain performance in zero-shot settings.

End-to-end text-to-speech synthesis (TTS) can generate highly natural synthetic speech from raw text. However, rendering the correct pitch accents is still a challenging problem for end-to-end TTS. To tackle the challenge of rendering correct pitch accent in Japanese end-to-end TTS, we adopt PnG~BERT, a self-supervised pretrained model in the character and phoneme domain for TTS. We investigate the effects of features captured by PnG~BERT on Japanese TTS by modifying the fine-tuning condition to determine the conditions helpful inferring pitch accents. We manipulate content of PnG~BERT features from being text-oriented to speech-oriented by changing the number of fine-tuned layers during TTS. In addition, we teach PnG~BERT pitch accent information by fine-tuning with tone prediction as an additional downstream task. Our experimental results show that the features of PnG~BERT captured by pretraining contain information helpful inferring pitch accent, and PnG~BERT outperforms baseline Tacotron on accent correctness in a listening test.

With the evolution of power systems as it is becoming more intelligent and interactive system while increasing in flexibility with a larger penetration of renewable energy sources, demand prediction on a short-term resolution will inevitably become more and more crucial in designing and managing the future grid, especially when it comes to an individual household level. Projecting the demand for electricity for a single energy user, as opposed to the aggregated power consumption of residential load on a wide scale, is difficult because of a considerable number of volatile and uncertain factors. This paper proposes a customized GRU (Gated Recurrent Unit) and Long Short-Term Memory (LSTM) architecture to address this challenging problem. LSTM and GRU are comparatively newer and among the most well-adopted deep learning approaches. The electricity consumption datasets were obtained from individual household smart meters. The comparison shows that the LSTM model performs better for home-level forecasting than alternative prediction techniques-GRU in this case. To compare the NN-based models with contrast to the conventional statistical technique-based model, ARIMA based model was also developed and benchmarked with LSTM and GRU model outcomes in this study to show the performance of the proposed model on the collected time series data.

Monitoring machine learning systems post deployment is critical to ensure the reliability of the systems. Particularly importance is the problem of monitoring the performance of machine learning systems across all the data subgroups (subpopulations). In practice, this process could be prohibitively expensive as the number of data subgroups grows exponentially with the number of input features, and the process of labelling data to evaluate each subgroup's performance is costly. In this paper, we propose an efficient framework for monitoring subgroup performance of machine learning systems. Specifically, we aim to find the data subgroup with the worst performance using a limited number of labeled data. We mathematically formulate this problem as an optimization problem with an expensive black-box objective function, and then suggest to use Bayesian optimization to solve this problem. Our experimental results on various real-world datasets and machine learning systems show that our proposed framework can retrieve the worst-performing data subgroup effectively and efficiently.

A widely acknowledged shortcoming of WordNet is that it lacks a distinction between word meanings which are systematically related (polysemy), and those which are coincidental (homonymy). Several previous works have attempted to fill this gap, by inferring this information using computational methods. We revisit this task, and exploit recent advances in language modelling to synthesise homonymy annotation for Princeton WordNet. Previous approaches treat the problem using clustering methods; by contrast, our method works by linking WordNet to the Oxford English Dictionary, which contains the information we need. To perform this alignment, we pair definitions based on their proximity in an embedding space produced by a Transformer model. Despite the simplicity of this approach, our best model attains an F1 of .97 on an evaluation set that we annotate. The outcome of our work is a high-quality homonymy annotation layer for Princeton WordNet, which we release.

We propose JFP, a Joint Future Prediction model that can learn to generate accurate and consistent multi-agent future trajectories. For this task, many different methods have been proposed to capture social interactions in the encoding part of the model, however, considerably less focus has been placed on representing interactions in the decoder and output stages. As a result, the predicted trajectories are not necessarily consistent with each other, and often result in unrealistic trajectory overlaps. In contrast, we propose an end-to-end trainable model that learns directly the interaction between pairs of agents in a structured, graphical model formulation in order to generate consistent future trajectories. It sets new state-of-the-art results on Waymo Open Motion Dataset (WOMD) for the interactive setting. We also investigate a more complex multi-agent setting for both WOMD and a larger internal dataset, where our approach improves significantly on the trajectory overlap metrics while obtaining on-par or better performance on single-agent trajectory metrics.