Although language models (LMs) have boosted the performance of Question Answering, they still need plenty of data. Data annotation, in contrast, is a time-consuming process. This especially applies to Question Answering, where possibly large documents have to be parsed and annotated with questions and their corresponding answers. Furthermore, Question Answering models often only work well for the domain they were trained on. Since annotation is costly, we argue that domain-agnostic knowledge from LMs, such as linguistic understanding, is sufficient to create a well-curated dataset. With this motivation, we show that using large language models can improve Question Answering performance on various datasets in the few-shot setting compared to state-of-the-art approaches. For this, we perform data generation leveraging the Prompting framework, suggesting that language models contain valuable task-agnostic knowledge that can be used beyond the common pre-training/fine-tuning scheme. As a result, we consistently outperform previous approaches on few-shot Question Answering.

The increasing use of information technology has led to a significant share of energy consumption and carbon emissions from data centers. These contributions are expected to rise with the growing demand for big data analytics, increasing digitization, and the development of large artificial intelligence (AI) models. The need to address the environmental impact of software development has led to increased interest in green (sustainable) coding and claims that the use of AI models can lead to energy efficiency gains. Here, we provide an empirical study on green code and an overview of green coding practices, as well as metrics used to quantify the sustainability awareness of AI models. In this framework, we evaluate the sustainability of auto-generated code. The auto-generate codes considered in this study are produced by generative commercial AI language models, GitHub Copilot, OpenAI ChatGPT-3, and Amazon CodeWhisperer. Within our methodology, in order to quantify the sustainability awareness of these AI models, we propose a definition of the code's "green capacity", based on certain sustainability metrics. We compare the performance and green capacity of human-generated code and code generated by the three AI language models in response to easy-to-hard problem statements. Our findings shed light on the current capacity of AI models to contribute to sustainable software development.

The 1x1 convolution is trained to map from a hidden layer of the classification or semantic Critical applications, such as in the medical field, segmentation network into a hidden layer of the GAN require the rapid provision of additional information generator. Utilizing this mapping, we can quickly visualize to interpret decisions made by deep learning activations of the classification or semantic segmentation methods. In this work, we propose a fast and network, by transferring them through the convolutional accurate method to visualize activations of classification connection into the GAN generator, i.e., we use the GAN and semantic segmentation networks by generator as a decoder to invert the classification or semantic stitching them with a GAN generator utilizing segmentation network.

Neural approaches have become very popular in the domain of Question Answering, however they require a large amount of annotated data. Furthermore, they often yield very good performance but only in the domain they were trained on. In this work we propose a novel approach that combines data augmentation via question-answer generation with Active Learning to improve performance in low resource settings, where the target domains are diverse in terms of difficulty and similarity to the source domain. We also investigate Active Learning for question answering in different stages, overall reducing the annotation effort of humans. For this purpose, we consider target domains in realistic settings, with an extremely low amount of annotated samples but with many unlabeled documents, which we assume can be obtained with little effort. Additionally, we assume sufficient amount of labeled data from the source domain is available. We perform extensive experiments to find the best setup for incorporating domain experts. Our findings show that our novel approach, where humans are incorporated as early as possible in the process, boosts performance in the low-resource, domain-specific setting, allowing for low-labeling-effort question answering systems in new, specialized domains. They further demonstrate how human annotation affects the performance of QA depending on the stage it is performed.

We present ADVISER - an open-source, multi-domain dialog system toolkit that enables the development of multi-modal (incorporating speech, text and vision), socially-engaged (e.g. emotion recognition, engagement level prediction and backchanneling) conversational agents. The final Python-based implementation of our toolkit is flexible, easy to use, and easy to extend not only for technically experienced users, such as machine learning researchers, but also for less technically experienced users, such as linguists or cognitive scientists, thereby providing a flexible platform for collaborative research. Link to open-source code: https://github.com/DigitalPhonetics/adviser

Neural networks have recently been established as a viable classification method for imaging mass spectrometry data for tumor typing. For multi-laboratory scenarios however, certain confounding factors may strongly impede their performance. In this work, we introduce Deep Relevance Regularization, a method of restricting what the neural network can focus on during classification, in order to improve the classification performance. We demonstrate how Deep Relevance Regularization robustifies neural networks against confounding factors on a challenging inter-lab dataset consisting of breast and ovarian carcinoma. We further show that this makes the relevance map - a way of visualizing the discriminative parts of the mass spectrum - sparser, thereby making the classifier easier to interpret.

In this case we used the Ram-Lak filter. If the measurements are noisy, FBP reconstructions tend to include streaking artifacts. A typical approach to overcome this problem is to apply some kind of post-processing such as denoising. Recent works [9, 18, 37] have successfully used convolutional neural networks, such as the U-Net [29]. The idea is to train a neural network to create clean reconstructions out of the noisy FBP results. In our implementation we used a U-Net-like architecture which is shown in Figure 4 and is similar to the one used in [21]. There, the authors show that such an architecture is a good image prior, i.e., its output is biased towards natural images, for example, noise-free images. Training was performed by minimizing the mean squared error loss with the Adam algorithm [20] for 20 epochs with batch size 64 and learning rate starting at 0 .01

Flow-based deep generative models learn data distributions by transforming a simple base distribution into a complex distribution via a set of invertible transformations. Due to the invertibility, such models can score unseen data samples by computing their exact likelihood under the learned distribution. This makes flow-based models a perfect tool for novelty detection, an anomaly detection technique where unseen data samples are classified as normal or abnormal by scoring them against a learned model of normal data. We show that normalizing flows can be used as novelty detectors in time series. Two flow-based models, Masked Autoregressive Flows and Free-form Jacobian of Reversible Dynamics restricted by autoregressive MADE networks, are tested on synthetic data and motor current data from an industrial machine and achieve good results, outperforming a conventional novelty detection method, the Local Outlier Factor.