我们介绍了IST和Unmabel对WMT 2022关于质量估计（QE）的共享任务的共同贡献。我们的团队参与了所有三个子任务：（i）句子和单词级质量预测；（ii）可解释的量化宽松；（iii）关键错误检测。对于所有任务，我们在彗星框架之上构建，将其与OpenKIWI的预测估计架构连接，并为其配备单词级序列标记器和解释提取器。我们的结果表明，在预处理过程中合并参考可以改善下游任务上多种语言对的性能，并且通过句子和单词级别的目标共同培训可以进一步提高。此外，将注意力和梯度信息结合在一起被证明是提取句子级量化量化宽松模型的良好解释的首要策略。总体而言，我们的意见书在几乎所有语言对的所有三个任务中都取得了最佳的结果。

在本文中，我们根据两个模型提出了一个端到端情感感知的对话代理：答复情绪预测模型，该模型利用对话的上下文来预测适当的情感，以便代理人在其答复中表达表达；以及一个基于预测的情感和对话的上下文的条件的文本生成模型，以产生既适合上下文又适合情感的答复。此外，我们建议使用情感分类模型来评估代理商在模型开发过程中表达的情感。这使我们能够自动评估代理。自动和人类评估结果都表明，用预定义的句子集明确指导文本生成模型导致了明确的改进，包括表达的情感和生成文本的质量。

Trainable evaluation metrics for machine translation (MT) exhibit strong correlation with human judgements, but they are often hard to interpret and might produce unreliable scores under noisy or out-of-domain data. Recent work has attempted to mitigate this with simple uncertainty quantification techniques (Monte Carlo dropout and deep ensembles), however these techniques (as we show) are limited in several ways -- for example, they are unable to distinguish between different kinds of uncertainty, and they are time and memory consuming. In this paper, we propose more powerful and efficient uncertainty predictors for MT evaluation, and we assess their ability to target different sources of aleatoric and epistemic uncertainty. To this end, we develop and compare training objectives for the COMET metric to enhance it with an uncertainty prediction output, including heteroscedastic regression, divergence minimization, and direct uncertainty prediction. Our experiments show improved results on uncertainty prediction for the WMT metrics task datasets, with a substantial reduction in computational costs. Moreover, they demonstrate the ability of these predictors to address specific uncertainty causes in MT evaluation, such as low quality references and out-of-domain data.

Credit scoring models are the primary instrument used by financial institutions to manage credit risk. The scarcity of research on behavioral scoring is due to the difficult data access. Financial institutions have to maintain the privacy and security of borrowers' information refrain them from collaborating in research initiatives. In this work, we present a methodology that allows us to evaluate the performance of models trained with synthetic data when they are applied to real-world data. Our results show that synthetic data quality is increasingly poor when the number of attributes increases. However, creditworthiness assessment models trained with synthetic data show a reduction of 3\% of AUC and 6\% of KS when compared with models trained with real data. These results have a significant impact since they encourage credit risk investigation from synthetic data, making it possible to maintain borrowers' privacy and to address problems that until now have been hampered by the availability of information.

Target Propagation (TP) is a biologically more plausible algorithm than the error backpropagation (BP) to train deep networks, and improving practicality of TP is an open issue. TP methods require the feedforward and feedback networks to form layer-wise autoencoders for propagating the target values generated at the output layer. However, this causes certain drawbacks; e.g., careful hyperparameter tuning is required to synchronize the feedforward and feedback training, and frequent updates of the feedback path are usually required than that of the feedforward path. Learning of the feedforward and feedback networks is sufficient to make TP methods capable of training, but is having these layer-wise autoencoders a necessary condition for TP to work? We answer this question by presenting Fixed-Weight Difference Target Propagation (FW-DTP) that keeps the feedback weights constant during training. We confirmed that this simple method, which naturally resolves the abovementioned problems of TP, can still deliver informative target values to hidden layers for a given task; indeed, FW-DTP consistently achieves higher test performance than a baseline, the Difference Target Propagation (DTP), on four classification datasets. We also present a novel propagation architecture that explains the exact form of the feedback function of DTP to analyze FW-DTP.

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

Despite the impact of psychiatric disorders on clinical health, early-stage diagnosis remains a challenge. Machine learning studies have shown that classifiers tend to be overly narrow in the diagnosis prediction task. The overlap between conditions leads to high heterogeneity among participants that is not adequately captured by classification models. To address this issue, normative approaches have surged as an alternative method. By using a generative model to learn the distribution of healthy brain data patterns, we can identify the presence of pathologies as deviations or outliers from the distribution learned by the model. In particular, deep generative models showed great results as normative models to identify neurological lesions in the brain. However, unlike most neurological lesions, psychiatric disorders present subtle changes widespread in several brain regions, making these alterations challenging to identify. In this work, we evaluate the performance of transformer-based normative models to detect subtle brain changes expressed in adolescents and young adults. We trained our model on 3D MRI scans of neurotypical individuals (N=1,765). Then, we obtained the likelihood of neurotypical controls and psychiatric patients with early-stage schizophrenia from an independent dataset (N=93) from the Human Connectome Project. Using the predicted likelihood of the scans as a proxy for a normative score, we obtained an AUROC of 0.82 when assessing the difference between controls and individuals with early-stage schizophrenia. Our approach surpassed recent normative methods based on brain age and Gaussian Process, showing the promising use of deep generative models to help in individualised analyses.

Weakly-supervised object detection (WSOD) models attempt to leverage image-level annotations in lieu of accurate but costly-to-obtain object localization labels. This oftentimes leads to substandard object detection and localization at inference time. To tackle this issue, we propose D2DF2WOD, a Dual-Domain Fully-to-Weakly Supervised Object Detection framework that leverages synthetic data, annotated with precise object localization, to supplement a natural image target domain, where only image-level labels are available. In its warm-up domain adaptation stage, the model learns a fully-supervised object detector (FSOD) to improve the precision of the object proposals in the target domain, and at the same time learns target-domain-specific and detection-aware proposal features. In its main WSOD stage, a WSOD model is specifically tuned to the target domain. The feature extractor and the object proposal generator of the WSOD model are built upon the fine-tuned FSOD model. We test D2DF2WOD on five dual-domain image benchmarks. The results show that our method results in consistently improved object detection and localization compared with state-of-the-art methods.

The renewed interest from the scientific community in machine learning (ML) is opening many new areas of research. Here we focus on how novel trends in ML are providing opportunities to improve the field of computational fluid dynamics (CFD). In particular, we discuss synergies between ML and CFD that have already shown benefits, and we also assess areas that are under development and may produce important benefits in the coming years. We believe that it is also important to emphasize a balanced perspective of cautious optimism for these emerging approaches

In the field of reinforcement learning, because of the high cost and risk of policy training in the real world, policies are trained in a simulation environment and transferred to the corresponding real-world environment. However, the simulation environment does not perfectly mimic the real-world environment, lead to model misspecification. Multiple studies report significant deterioration of policy performance in a real-world environment. In this study, we focus on scenarios involving a simulation environment with uncertainty parameters and the set of their possible values, called the uncertainty parameter set. The aim is to optimize the worst-case performance on the uncertainty parameter set to guarantee the performance in the corresponding real-world environment. To obtain a policy for the optimization, we propose an off-policy actor-critic approach called the Max-Min Twin Delayed Deep Deterministic Policy Gradient algorithm (M2TD3), which solves a max-min optimization problem using a simultaneous gradient ascent descent approach. Experiments in multi-joint dynamics with contact (MuJoCo) environments show that the proposed method exhibited a worst-case performance superior to several baseline approaches.