In the field of wildlife observation and conservation, approaches involving machine learning on audio recordings are becoming increasingly popular. Unfortunately, available datasets from this field of research are often not optimal learning material; Samples can be weakly labeled, of different lengths or come with a poor signal-to-noise ratio. In this work, we introduce a generalized approach that first relabels subsegments of MEL spectrogram representations, to achieve higher performances on the actual multi-class classification tasks. For both the binary pre-sorting and the classification, we make use of convolutional neural networks (CNN) and various data-augmentation techniques. We showcase the results of this approach on the challenging \textit{ComparE 2021} dataset, with the task of classifying between different primate species sounds, and report significantly higher Accuracy and UAR scores in contrast to comparatively equipped model baselines.

Automated news credibility and fact-checking at scale require accurately predicting news factuality and media bias. This paper introduces a large sentence-level dataset, titled "FactNews", composed of 6,191 sentences expertly annotated according to factuality and media bias definitions proposed by AllSides. We use FactNews to assess the overall reliability of news sources, by formulating two text classification problems for predicting sentence-level factuality of news reporting and bias of media outlets. Our experiments demonstrate that biased sentences present a higher number of words compared to factual sentences, besides having a predominance of emotions. Hence, the fine-grained analysis of subjectivity and impartiality of news articles provided promising results for predicting the reliability of media outlets. Finally, due to the severity of fake news and political polarization in Brazil, and the lack of research for Portuguese, both dataset and baseline were proposed for Brazilian Portuguese.

Narrative summarization aims to produce a distilled version of a narrative to describe its most salient events and characters. Summarizing a narrative is challenging as it requires an understanding of event causality and character behaviors. To encourage research in this direction, we propose NarraSum, a large-scale narrative summarization dataset. It contains 122K narrative documents, which are collected from plot descriptions of movies and TV episodes with diverse genres, and their corresponding abstractive summaries. Experiments show that there is a large performance gap between humans and the state-of-the-art summarization models on NarraSum. We hope that this dataset will promote future research in summarization, as well as broader studies of natural language understanding and generation. The dataset is available at https://github.com/zhaochaocs/narrasum.

'The Five' co-hosts discuss new AI bot ChatGPT and the impact artificial intelligence will have on future jobs. Church leaders and volunteers will soon have access to an artificial intelligence platform that aims to shave hours off their day-to-day tasks by generating content from sermons to engage fellow Christians when they are not in the pews. Upcoming platform Pulpit AI, founded by Michael Whittle, is expected to launch later this summer and will serve as a tool for Christian leaders looking to take the tedious work out of crafting religious blog posts, devotionals and prayer guides and social media posts. "We want to help pastors of small to medium-sized churches be able to make content for their congregations to interact with throughout the week and on social media," Whittle told Fox News Digital. "We think every pastor should, if they want, have a digital signal to their congregations beyond the sermon. "Most small to medium-sized churches have small or completely volunteer staff, so they have zero operational leverage when it comes to media and resources for their church," he added. "If we can help a church media team get past the blank page, we can not only save them crazy amounts of time, we can help every church become a resourcing church for their people." 'AI JESUS' TALKS DATING, RELATIONSHIPS, MORALS -- EVEN OFFERS VIDEO-GAMING TIPS A congregant reads a referred passage from her Bible during services at Highland Colony Baptist Church in Ridgeland, Mississippi, Nov. 29, 2020. Puplit AI "doesn't and never will" generate sermons, instead it serves as a tool where the user uploads a sermon or religious podcast in order to repurpose it into "social media highlights, blog posts, discussion questions, and the other content churches use to reach their congregations and communities day in and day out," Whittle said. "Pulpit AI analyzes long form audio and video, then repurposes that into various forms of content," Whittle said. "Pulpit AI's output is taken directly from the source material.

In this article, a tutorial introduction to visual-inertial navigation(VIN) is presented. Visual and inertial perception are two complementary sensing modalities. Cameras and inertial measurement units (IMU) are the corresponding sensors for these two modalities. The low cost and light weight of camera-IMU sensor combinations make them ubiquitous in robotic navigation. Visual-inertial Navigation is a state estimation problem, that estimates the ego-motion and local environment of the sensor platform. This paper presents visual-inertial navigation in the classical state estimation framework, first illustrating the estimation problem in terms of state variables and system models, including related quantities representations (Parameterizations), IMU dynamic and camera measurement models, and corresponding general probabilistic graphical models (Factor Graph). Secondly, we investigate the existing model-based estimation methodologies, these involve filter-based and optimization-based frameworks and related on-manifold operations. We also discuss the calibration of some relevant parameters, also initialization of state of interest in optimization-based frameworks. Then the evaluation and improvement of VIN in terms of accuracy, efficiency, and robustness are discussed. Finally, we briefly mention the recent development of learning-based methods that may become alternatives to traditional model-based methods.

In this paper, we explore the new design space of extra-linguistic cues inspired by graphical tropes used in graphic novels and animation to enhance the expressiveness of social robots. To achieve this, we identified a set of cues that can be used to generate expressions, including smoke/steam/fog, water droplets, and bubbles. We prototyped devices that can generate these fluid expressions for a robot and conducted design sessions where eight designers explored the use and utility of the cues in conveying the robot's internal states in various design scenarios. Our analysis of the 22 designs, the associated design justifications, and the interviews with designers revealed patterns in how each cue was used, how they were combined with nonverbal cues, and where the participants drew their inspiration from. These findings informed the design of an integrated module called EmoPack, which can be used to augment the expressive capabilities of any robot platform.

Review score prediction requires review text understanding, a critical real-world application of natural language processing. Due to dissimilar text domains in product reviews, a common practice is fine-tuning BERT models upon reviews of differing domains. However, there has not yet been an empirical study of cross-domain behaviors of BERT models in the various tasks of product review understanding. In this project, we investigate text classification BERT models fine-tuned on single-domain and multi-domain Amazon review data. In our findings, though single-domain models achieved marginally improved performance on their corresponding domain compared to multi-domain models, multi-domain models outperformed single-domain models when evaluated on multi-domain data, single-domain data the single-domain model was not fine-tuned on, and on average when considering all tests. Though slight increases in accuracy can be achieved through single-domain model fine-tuning, computational resources and costs can be reduced by utilizing multi-domain models that perform well across domains.

Increasing attention is being paid to millimeter-wave (mmWave), 30 GHz to 300 GHz, and terahertz (THz), 300 GHz to 10 THz, sensing applications including security sensing, industrial packaging, medical imaging, and non-destructive testing. Traditional methods for perception and imaging are challenged by novel data-driven algorithms that offer improved resolution, localization, and detection rates. Over the past decade, deep learning technology has garnered substantial popularity, particularly in perception and computer vision applications. Whereas conventional signal processing techniques are more easily generalized to various applications, hybrid approaches where signal processing and learning-based algorithms are interleaved pose a promising compromise between performance and generalizability. Furthermore, such hybrid algorithms improve model training by leveraging the known characteristics of radio frequency (RF) waveforms, thus yielding more efficiently trained deep learning algorithms and offering higher performance than conventional methods. This dissertation introduces novel hybrid-learning algorithms for improved mmWave imaging systems applicable to a host of problems in perception and sensing. Various problem spaces are explored, including static and dynamic gesture classification; precise hand localization for human computer interaction; high-resolution near-field mmWave imaging using forward synthetic aperture radar (SAR); SAR under irregular scanning geometries; mmWave image super-resolution using deep neural network (DNN) and Vision Transformer (ViT) architectures; and data-level multiband radar fusion using a novel hybrid-learning architecture. Furthermore, we introduce several novel approaches for deep learning model training and dataset synthesis.

Pretrained language models are publicly available and constantly finetuned for various real-life applications. As they become capable of grasping complex contextual information, harmful biases are likely increasingly intertwined with those models. This paper analyses gender bias in BERT models with two main contributions: First, a novel bias measure is introduced, defining biases as the difference in sentiment valuation of female and male sample versions. Second, we comprehensively analyse BERT's biases on the example of a realistic IMDB movie classifier. By systematically varying elements of the training pipeline, we can conclude regarding their impact on the final model bias. Seven different public BERT models in nine training conditions, i.e. 63 models in total, are compared. Almost all conditions yield significant gender biases. Results indicate that reflected biases stem from public BERT models rather than task-specific data, emphasising the weight of responsible usage.

Adversarial robustness, domain generalization and dataset biases are three active lines of research contributing to out-of-distribution (OOD) evaluation on neural NLP models. However, a comprehensive, integrated discussion of the three research lines is still lacking in the literature. In this survey, we 1) compare the three lines of research under a unifying definition; 2) summarize the data-generating processes and evaluation protocols for each line of research; and 3) emphasize the challenges and opportunities for future work.