Diffusion models have achieved great success in modeling continuous data modalities such as images, audio, and video, but have seen limited use in discrete domains such as language. Recent attempts to adapt diffusion to language have presented diffusion as an alternative to existing pretrained language models. We view diffusion and existing language models as complementary. We demonstrate that encoder-decoder language models can be utilized to efficiently learn high-quality language autoencoders. We then demonstrate that continuous diffusion models can be learned in the latent space of the language autoencoder, enabling us to sample continuous latent representations that can be decoded into natural language with the pretrained decoder. We validate the effectiveness of our approach for unconditional, class-conditional, and sequence-to-sequence language generation. We demonstrate across multiple diverse data sets that our latent language diffusion models are significantly more effective than previous diffusion language models.

This paper addresses the task of automatically detecting narrative structures in raw texts. Previous works have utilized the oral narrative theory by Labov and Waletzky to identify various narrative elements in personal stories texts. Instead, we direct our focus to news articles, motivated by their growing social impact as well as their role in creating and shaping public opinion. We introduce CompRes -- the first dataset for narrative structure in news media. We describe the process in which the dataset was constructed: first, we designed a new narrative annotation scheme, better suited for news media, by adapting elements from the narrative theory of Labov and Waletzky (Complication and Resolution) and adding a new narrative element of our own (Success); then, we used that scheme to annotate a set of 29 English news articles (containing 1,099 sentences) collected from news and partisan websites. We use the annotated dataset to train several supervised models to identify the different narrative elements, achieving an $F_1$ score of up to 0.7. We conclude by suggesting several promising directions for future work.

Ratings are frequently used to evaluate and compare subjects in various applications, from education to healthcare, because ratings provide succinct yet credible measures for comparing subjects. However, when multiple rating lists are combined or considered together, subjects often have missing ratings, because most rating lists do not rate every subject in the combined list. In this study, we propose analyses on missing value patterns using six real-world data sets in various applications, as well as the conditions for applicability of imputation algorithms. Based on the special structures and properties derived from the analyses, we propose optimization models and algorithms that minimize the total rating discordance across rating providers to impute missing ratings in the combined rating lists, using only the known rating information. The total rating discordance is defined as the sum of the pairwise discordance metric, which can be written as a quadratic function. Computational experiments based on real-world and synthetic rating data sets show that the proposed methods outperform the state-of-the-art general imputation methods in the literature in terms of imputation accuracy.

There is no easy way to explain the sum of Google's knowledge. A growing web of hundreds of billions of websites, more data than even 100,000 of the most expensive iPhones mashed together could possibly store. But right now, I can say this: Google is confused about whether there's an African country beginning with the letter k. I've asked the search engine to name it. "What is an African country beginning with K?" In response, the site has produced a "featured snippet" answer--one of those chunks of text that you can read directly on the results page, without navigating to another website.

As the other members of the Beatles sing and play, Lennon, ever the cut-up, clowns around, bouncing from one leg to the other with a grin on his face. His hands move like flippers, turned out at an odd angle and making frantic circles in the air, as if he's wiping down an invisible window. And as his body moves from side to side, his head seems to lag slightly behind it. The larkish ebullience feels strained and off-kilter, like an audience that wants to clap along but can't find the beat. The music video for "Now and Then," which has been billed as "the last Beatles song," starts off as an affectionate nostalgia trip, intercutting present-day footage of the two surviving Beatles with archival footage of their late bandmates.

When Texas-based copywriter Dustin Ballard released a cover of Aqua's 1997 Europop hit "Barbie Girl" this summer using an AI-generated version of Johnny Cash's voice, he was surprised by its reception. "I actually expected more of a backlash," he says. Earlier this fall, when he followed up with AI Johnny Cash singing Taylor Swift's "Blank Space," the feedback was unexpectedly positive once again. "This is hauntingly beautiful," the top comment reads. "It absolutely slaps," Futurism wrote.

The existence of adversarial examples brings huge concern for people to apply Deep Neural Networks (DNNs) in safety-critical tasks. However, how to generate adversarial examples with categorical data is an important problem but lack of extensive exploration. Previously established methods leverage greedy search method, which can be very time-consuming to conduct successful attack. This also limits the development of adversarial training and potential defenses for categorical data. To tackle this problem, we propose Probabilistic Categorical Adversarial Attack (PCAA), which transfers the discrete optimization problem to a continuous problem that can be solved efficiently by Projected Gradient Descent. In our paper, we theoretically analyze its optimality and time complexity to demonstrate its significant advantage over current greedy based attacks. Moreover, based on our attack, we propose an efficient adversarial training framework. Through a comprehensive empirical study, we justify the effectiveness of our proposed attack and defense algorithms.

In this paper, we propose a ground-based monocular UAV localisation system that detects and localises an LED marker attached to the underside of a UAV. Our system removes the need for extensive infrastructure and calibration unlike existing technologies such as UWB, radio frequency and multi-camera systems often used for localisation in GPS-denied environment. To improve deployablity for real-world applications without the need to collect extensive real dataset, we train a CNN on synthetic binary images as opposed to using real images in existing monocular UAV localisation methods, and factor in the camera's zoom to allow tracking of UAVs flying at further distances. We propose NoisyCutout algorithm for augmenting synthetic binary images to simulate binary images processed from real images and show that it improves localisation accuracy as compared to using existing salt-and-pepper and Cutout augmentation methods. We also leverage uncertainty propagation to modify the CNN's loss function and show that this also improves localisation accuracy. Real-world experiments are conducted to evaluate our methods and we achieve an overall 3D RMSE of approximately 0.41m.

Music has been commonly recognized as a means of expressing emotions. In this sense, an intense debate emerges from the need to verbalize musical emotions. This concern seems highly relevant today, considering the exponential growth of natural language processing using deep learning models where it is possible to prompt semantic propositions to generate music automatically. This scoping review aims to analyze and discuss the possibilities of music generation conditioned by emotions. To address this topic, we propose a historical perspective that encompasses the different disciplines and methods contributing to this topic. In detail, we review two main paradigms adopted in automatic music generation: rules-based and machine-learning models. Of note are the deep learning architectures that aim to generate high-fidelity music from textual descriptions. These models raise fundamental questions about the expressivity of music, including whether emotions can be represented with words or expressed through them. We conclude that overcoming the limitation and ambiguity of language to express emotions through music, some of the use of deep learning with natural language has the potential to impact the creative industries by providing powerful tools to prompt and generate new musical works.

Variational Autoencoders (VAEs) have proven to be effective models for producing latent representations of cognitive and semantic value. We assess the degree to which VAEs trained on a prototypical tonal music corpus of 371 Bach's chorales define latent spaces representative of the circle of fifths and the hierarchical relation of each key component pitch as drawn in music cognition. In detail, we compare the latent space of different VAE corpus encodings -- Piano roll, MIDI, ABC, Tonnetz, DFT of pitch, and pitch class distributions -- in providing a pitch space for key relations that align with cognitive distances. We evaluate the model performance of these encodings using objective metrics to capture accuracy, mean square error (MSE), KL-divergence, and computational cost. The ABC encoding performs the best in reconstructing the original data, while the Pitch DFT seems to capture more information from the latent space. Furthermore, an objective evaluation of 12 major or minor transpositions per piece is adopted to quantify the alignment of 1) intra- and inter-segment distances per key and 2) the key distances to cognitive pitch spaces. Our results show that Pitch DFT VAE latent spaces align best with cognitive spaces and provide a common-tone space where overlapping objects within a key are fuzzy clusters, which impose a well-defined order of structural significance or stability -- i.e., a tonal hierarchy. Tonal hierarchies of different keys can be used to measure key distances and the relationships of their in-key components at multiple hierarchies (e.g., notes and chords). The implementation of our VAE and the encodings framework are made available online.