Stance detection is the task of determining the viewpoint expressed in a text towards a given target. A specific direction within the task focuses on cross-target stance detection, where a model trained on samples pertaining to certain targets is then applied to a new, unseen target. With the increasing need to analyze and mining viewpoints and opinions online, the task has recently seen a significant surge in interest. This review paper examines the advancements in cross-target stance detection over the last decade, highlighting the evolution from basic statistical methods to contemporary neural and LLM-based models. These advancements have led to notable improvements in accuracy and adaptability. Innovative approaches include the use of topic-grouped attention and adversarial learning for zero-shot detection, as well as fine-tuning techniques that enhance model robustness. Additionally, prompt-tuning methods and the integration of external knowledge have further refined model performance. A comprehensive overview of the datasets used for evaluating these models is also provided, offering valuable insights into the progress and challenges in the field. We conclude by highlighting emerging directions of research and by suggesting avenues for future work in the task.

Transformer neural networks (TNN) have been widely utilized on a diverse range of applications, including natural language processing (NLP), machine translation, and computer vision (CV). Their widespread adoption has been primarily driven by the exceptional performance of their multi-head self-attention block used to extract key features from sequential data. The multi-head self-attention block is followed by feedforward neural networks, which play a crucial role in introducing non-linearity to assist the model in learning complex patterns. Despite the popularity of TNNs, there has been limited numbers of hardware accelerators targeting these two critical blocks. Most prior works have concentrated on sparse architectures that are not flexible for popular TNN variants. This paper introduces \textit{ProTEA}, a runtime programmable accelerator tailored for the dense computations of most of state-of-the-art transformer encoders. \textit{ProTEA} is designed to reduce latency by maximizing parallelism. We introduce an efficient tiling of large matrices that can distribute memory and computing resources across different hardware components within the FPGA. We provide run time evaluations of \textit{ProTEA} on a Xilinx Alveo U55C high-performance data center accelerator card. Experimental results demonstrate that \textit{ProTEA} can host a wide range of popular transformer networks and achieve near optimal performance with a tile size of 64 in the multi-head self-attention block and 6 in the feedforward networks block when configured with 8 parallel attention heads, 12 layers, and an embedding dimension of 768 on the U55C. Comparative results are provided showing \textit{ProTEA} is 2.5$\times$ faster than an NVIDIA Titan XP GPU. Results also show that it achieves 1.3 -- 2.8$\times$ speed up compared with current state-of-the-art custom designed FPGA accelerators.

Natural language processing (NLP) has witnessed a profound impact of large language models (LLMs) that excel in a multitude of tasks. However, the limitation of LLMs in multilingual settings, particularly in underrepresented languages, remains a significant hurdle. This thesis aims to bridge the gap in NLP research and development by focusing on underrepresented languages. A comprehensive evaluation of LLMs is conducted to assess their capabilities in these languages, revealing the challenges of multilingual and multicultural generalization. Addressing the multilingual generalization gap, this thesis proposes data-and-compute-efficient methods to mitigate the disparity in LLM ability in underrepresented languages, allowing better generalization on underrepresented languages without the loss of task generalization ability. The proposed solutions cover cross-lingual continual instruction tuning, retrieval-based cross-lingual in-context learning, and in-context query alignment. Furthermore, a novel method to measure cultural values alignment between LLMs operating in different languages is proposed, ensuring cultural sensitivity and inclusivity. These contributions aim to enhance the multilingual and multicultural alignment of LLMs in underrepresented languages, ultimately advancing the NLP field toward greater equality and inclusiveness.

We study language ideologies in text produced by LLMs through a case study on English gendered language reform (related to role nouns like congressperson/-woman/-man, and singular they). First, we find political bias: when asked to use language that is "correct" or "natural", LLMs use language most similarly to when asked to align with conservative (vs. progressive) values. This shows how LLMs' metalinguistic preferences can implicitly communicate the language ideologies of a particular political group, even in seemingly non-political contexts. Second, we find LLMs exhibit internal inconsistency: LLMs use gender-neutral variants more often when more explicit metalinguistic context is provided. This shows how the language ideologies expressed in text produced by LLMs can vary, which may be unexpected to users. We discuss the broader implications of these findings for value alignment.

Understanding satire and humor is a challenging task for even current Vision-Language models. In this paper, we propose the challenging tasks of Satirical Image Detection (detecting whether an image is satirical), Understanding (generating the reason behind the image being satirical), and Completion (given one half of the image, selecting the other half from 2 given options, such that the complete image is satirical) and release a high-quality dataset YesBut, consisting of 2547 images, 1084 satirical and 1463 non-satirical, containing different artistic styles, to evaluate those tasks. Each satirical image in the dataset depicts a normal scenario, along with a conflicting scenario which is funny or ironic. Despite the success of current Vision-Language Models on multimodal tasks such as Visual QA and Image Captioning, our benchmarking experiments show that such models perform poorly on the proposed tasks on the YesBut Dataset in Zero-Shot Settings w.r.t both automated as well as human evaluation. Additionally, we release a dataset of 119 real, satirical photographs for further research. The dataset and code are available at https://github.com/abhi1nandy2/yesbut_dataset.

We present a method for automatically producing human-like vocal imitations of sounds: the equivalent of "sketching," but for auditory rather than visual representation. Starting with a simulated model of the human vocal tract, we first try generating vocal imitations by tuning the model's control parameters to make the synthesized vocalization match the target sound in terms of perceptually-salient auditory features. Then, to better match human intuitions, we apply a cognitive theory of communication to take into account how human speakers reason strategically about their listeners. Finally, we show through several experiments and user studies that when we add this type of communicative reasoning to our method, it aligns with human intuitions better than matching auditory features alone does. This observation has broad implications for the study of depiction in computer graphics.

The text below arose from a course on'Mathematical Data Science' that I taught twice for final year BSc Mathematics students in the UK between 2019 and 2020. The notes presently cover the first part (roughly a third) of the course focussing on the characteristics and peculiarities of high-dimensional data. An improved version of the notes appeared as part of the textbook [7]; we refer the reader in particular to [7, Chapters 8 -12]. I would like to thank my former students who attended the course and helped me with their feedback to write these lecture notes. Concrete examples are as follows. Each user can give a rating from one to five stars for each movie. When doing medical diagnostic tests, we can represent a subject by the vector containing her/his results. These can include integers like antibody counts, real numbers like temperature, pairs of real numbers like blood pressure, or binary values like if a subject has tested positive or negative for a certain infection. If we name the users 1, 2, 3,..., we can represent user j in R Given such a high-dimensional data set A, classical tasks to analyze the data, or make predictions based on it, involve to compute distances between data points. This can be for example the classical euclidean distance (or any other p-norm), CHAPTER 1. THE CURSE OF HIGH DIMENSIONS 4 However, if d is very large, we are faced with the following two obstructions.

Technology AI What a major movie studio's AI deal could mean for the future of Hollywood Generative AI might save studios'millions and millions of dollars,' but at what cost? Breakthroughs, discoveries, and DIY tips sent every weekday. When Hollywood's actors took to the streets last year for a 118 day strike, many wielded signs reading "no digital clones," "AI is soulless," and "AI is not art." These ticked-off thespians were expressing a sentiment shared by a growing share of writers, video games voice actors, and many other creatives: generative AI tools, trained off their work, may threaten their jobs and shrink the entertainment industry. When the strike ended, actors were awarded new, hard-won protections against AI-generated clones .

Prince Harry says his father King Charles is'great' following their first meeting in 19 months... which was over a cup of tea and just 55 minutes long A DEI mayor, an inconvenient crime and video they never wanted you to see: MAUREEN CALLAHAN knows why the Left has sympathy for that killer... but none for his victim Tragedy as Charlie Kirk's wife left behind with two young children after conservative activist is fatally shot Sweater weather starts here - the cozy, chic pieces from Soft Surroundings you'll actually wear all season Fox News reveals new lineup and elevates star White House reporter who's sparred with Trump I tried the 30 cent'miracle chill pill' before a big event.. now I'm taking it for everything Carlos Alcaraz's new girlfriend revealed after US Open triumph... amid Emma Raducanu rumors Kimberly Guilfoyle urged to'stop with the lips' as she shows off drastic new look Knifeman accused of stabbing Ukrainian refugee to death gives chilling reason for the attack... as he speaks for the first time from jail on the murder that shocked America We only had one symptom we dismissed... but then we were diagnosed with the rarest form of melanoma MSNBC sparks outrage for'disgusting' Charlie Kirk comments following Utah shooting I was thrilled to finally sit in the cuck chair... now I fear my fantasy has destroyed my marriage: DEAR JANE READ MORE: Top brain surgeon who says he went to heaven reveals what it's like A baffling new theory to explain human consciousness has suggested it comes from hidden dimensions and is not just brain activity. A physicist claimed that we plug in to these invisible planes of the universe when making art, practicing science, pondering philosophy or dreaming, and this could explain the phenomenon that has evaded scientific understanding for centuries. Michael Pravica, a professor of physics at the University of Nevada, Las Vegas, has based the wild idea on hyperdimensionality, the idea that the universe is made up of more dimensions than just the four we perceive: height, length width and time. But his theory is highly controversial, with one scientist saying that the cornerstone of Pravica's theory'borders on science fiction.' 'The sheer fact that we can conceive of higher dimensions than four within our mind, within our mathematics, is a gift... it's something that transcends biology,' Pravica told Popular Mechanics . Scientists have been attempting to explain human consciousness and its origins for hundreds of years - and the theories run the gamut.

Things to Do in L.A. Tap to enable a layout that focuses on the article. Long Beach's Backyard Builders Program uses one-time funding that will provide as many as 10 homeowners low-to zero-interest loans of up to $250,000 to build Accessory Dwelling Units, or ADUs, on their lots. Eager to boost the supply of affordable housing, city officials in Long Beach devised a program that could help a limited number of homeowners build an extra unit on their land. But before they could launch it, they had to decide what to call it. "We've been playing with a name for a while," Mayor Rex Richardson said, noting that a news release touting the program had been delayed days because of christening purposes.