Event data, or structured records of ``who did what to whom'' that are automatically extracted from text, is an important source of data for scholars of international politics. The high cost of developing new event datasets, especially using automated systems that rely on hand-built dictionaries, means that most researchers draw on large, pre-existing datasets such as ICEWS rather than developing tailor-made event datasets optimized for their specific research question. This paper describes a ``bag of tricks'' for efficient, custom event data production, drawing on recent advances in natural language processing (NLP) that allow researchers to rapidly produce customized event datasets. The paper introduces techniques for training an event category classifier with active learning, identifying actors and the recipients of actions in text using large language models and standard machine learning classifiers and pretrained ``question-answering'' models from NLP, and resolving mentions of actors to their Wikipedia article to categorize them. We describe how these techniques produced the new POLECAT global event dataset that is intended to replace ICEWS, along with examples of how scholars can quickly produce smaller, custom event datasets. We publish example code and models to implement our new techniques.

Language modeling have shown impressive progress in generating compelling text with good accuracy and high semantic coherence. An interesting research direction is to augment these powerful models for specific applications using contextual information. In this work, we explore multi-modal language modeling for healthcare applications. We are interested in outcome prediction and patient triage in hospital emergency department based on text information in chief complaints and vital signs recorded at triage. We adapt Perceiver - a modality-agnostic transformer-based model that has shown promising results in several applications. Since vital-sign modality is represented in tabular format, we modified Perceiver position encoding to ensure permutation invariance. We evaluated the multi-modal language model for the task of diagnosis code prediction using MIMIC-IV ED dataset on 120K visits. In the experimental analysis, we show that mutli-modality improves the prediction performance compared with models trained solely on text or vital signs. We identified disease categories for which multi-modality leads to performance improvement and show that for these categories, vital signs have added predictive power. By analyzing the cross-attention layer, we show how multi-modality contributes to model predictions. This work gives interesting insights on the development of multi-modal language models for healthcare applications.

OpenAI has taken ChatGPT offline in Italy after the government's Data Protection Authority on Friday temporarily banned the chatbot and launched a probe over the artificial intelligence application's suspected breach of privacy rules. The agency, also known as Garante, accused Microsoft-backed OpenAI of failing to check the age of ChatGPT's users who are supposed to be aged 13 or above. ChatGPT has an "absence of any legal basis that justifies the massive collection and storage of personal data" to "train" the chatbot, Garante said. OpenAI has 20 days to respond with remedies or could risk a fine of up to 20 million euros ($21.68 million) or 4% of its annual worldwide turnover. OpenAI said it has disabled ChatGPT for users in Italy at the request of the Garante.

The present paper is about the participation of our team "techno" on CERIST'22 shared tasks. We used an available dataset "task1.c" related to covid-19 pandemic. It comprises 4128 tweets for sentiment analysis task and 8661 tweets for fake news detection task. We used natural language processing tools with the combination of the most renowned pre-trained language models BERT (Bidirectional Encoder Representations from Transformers). The results shows the efficacy of pre-trained language models as we attained an accuracy of 0.93 for the sentiment analysis task and 0.90 for the fake news detection task.

Recent advancements in diffusion models have enabled the generation of realistic deepfakes by writing textual prompts in natural language. While these models have numerous benefits across various sectors, they have also raised concerns about the potential misuse of fake images and cast new pressures on fake image detection. In this work, we pioneer a systematic study of the authenticity of fake images generated by state-of-the-art diffusion models. Firstly, we conduct a comprehensive study on the performance of contrastive and classification-based visual features. Our analysis demonstrates that fake images share common low-level cues, which render them easily recognizable. Further, we devise a multimodal setting wherein fake images are synthesized by different textual captions, which are used as seeds for a generator. Under this setting, we quantify the performance of fake detection strategies and introduce a contrastive-based disentangling strategy which let us analyze the role of the semantics of textual descriptions and low-level perceptual cues. Finally, we release a new dataset, called COCOFake, containing about 600k images generated from original COCO images.

Training-time defenses, known as adversarial training, incur high training costs and do not generalize to unseen attacks. Test-time defenses solve these issues but most existing test-time defenses require adapting the model weights, therefore they do not work on frozen models and complicate model memory management. The only test-time defense that does not adapt model weights aims to adapt the input with self-supervision tasks. However, we empirically found these self-supervision tasks are not sensitive enough to detect adversarial attacks accurately. In this paper, we propose DRAM, a novel defense method to detect and repair adversarial samples at test time via Masked autoencoder (MAE). We demonstrate how to use MAE losses to build a Kolmogorov-Smirnov test to detect adversarial samples. Moreover, we use the MAE losses to calculate input reversal vectors that repair adversarial samples resulting from previously unseen attacks. Results on large-scale ImageNet dataset show that, compared to all detection baselines evaluated, DRAM achieves the best detection rate (82% on average) on all eight adversarial attacks evaluated. For attack repair, DRAM improves the robust accuracy by 6% ~ 41% for standard ResNet50 and 3% ~ 8% for robust ResNet50 compared with the baselines that use contrastive learning and rotation prediction.

The algorithm known as backpropagation of errors [59, 32], or "backprop" for short, has long faced criticism concerning its neurobiological plausibility [10, 14, 56, 35, 15]. Despite powering the tremendous progress and success behind deep learning and its every-growing myriad of promising applications [57, 12], it is improbable that backprop is a viable model of learning in the brain, such as in cortical regions. Notably, there are both practical and biophysical issues [15, 35], and, among these issues, there is a lack of evidence that: 1) neural activities are explicitly stored to be used later for synaptic adjustment, 2) error derivatives are backpropagated along a global feedback pathway to generate teaching signals, 3) the error signals move back along the same neural pathways used to forward propagate information, and, 4) inference and learning are locked to be largely sequential (instead of massively parallel). Furthermore, when processing temporal data, it is certainly not the case that the neural circuitry of the brain is unfolded backward through time to adjust synapses [42] (as in backprop through time). Recently, there has been a growing interest in the research domain of brain-inspired computing, which focuses on developing algorithms and computational models that attempt to circumvent or resolve critical issues such as those highlighted above. Among the most powerful and promising ones is predictive coding (PC) [18, 48, 13, 4, 51, 41], and among the most recent ones is the forward-forward (FF) algorithm [19]. These alternatives offer different means of conducting credit assignments with performance similar to backprop, but to the contrary, are more likely consistent with and similar to real biological neuron learning (see Figure 1 for a graphical depiction and comparison of respective credit assignment setups). This paper will propose a novel model and learning process, the predictive forward-forward (PFF) process, that generalizes and combines FF and PC into a robust stochastic neural system that simultaneously learns a representation and generative model in a biologically-plausible fashion. Like the FF algorithm, the PFF procedure offers a promising, potentially helpful model of biological neural circuits, a potential candidate system for low-power analog hardware and neuromorphic circuits, and a potential backprop-alternative worthy of future investigation and study.

We derive high-dimensional scaling limits and fluctuations for the online least-squares Stochastic Gradient Descent (SGD) algorithm by taking the properties of the data generating model explicitly into consideration. Our approach treats the SGD iterates as an interacting particle system, where the expected interaction is characterized by the covariance structure of the input. Assuming smoothness conditions on moments of order up to eight orders, and without explicitly assuming Gaussianity, we establish the high-dimensional scaling limits and fluctuations in the form of infinite-dimensional Ordinary Differential Equations (ODEs) or Stochastic Differential Equations (SDEs). Our results reveal a precise three-step phase transition of the iterates; it goes from being ballistic, to diffusive, and finally to purely random behavior, as the noise variance goes from low, to moderate and finally to very-high noise setting. In the low-noise setting, we further characterize the precise fluctuations of the (scaled) iterates as infinite-dimensional SDEs. We also show the existence and uniqueness of solutions to the derived limiting ODEs and SDEs. Our results have several applications, including characterization of the limiting mean-square estimation or prediction errors and their fluctuations which can be obtained by analytically or numerically solving the limiting equations.

Ukraine has branded Russia's presidency of the UN Security Council for the month of April "a symbolic blow," joining a chorus of outrage from Western countries. Moscow assumes the presidency as part of its monthly rotation between the Security Council's 15 member states, with ties with the West at their lowest point since the Cold War over Russia's invasion of Ukraine. Andriy Yermak, the Ukrainian president's chief of staff, said Russia's tenure was a "symbolic blow." It is another symbolic blow to the rules-based system of international relations," he wrote on Twitter. Ukraine's Foreign Minister Dmytro Kuleba said Russia assuming the presidency was "a slap in the face to the international community". "I urge the current UNSC members to thwart any Russian attempts to abuse its presidency," he wrote on Twitter on Saturday, calling Russia "an outlaw on the UNSC". Moscow last chaired the council in February 2022, the same month it invaded Ukraine – prompting Kyiv to call for Russia's removal from the council. Russia will hold little influence on decisions but will be in charge of the agenda. Moscow has said Foreign Minister Sergey Lavrov is planning to chair a UN Security Council meeting this month on "effective multilateralism". Russian foreign ministry spokeswoman Maria Zakharova also said that Lavrov would lead a debate on the Middle East on April 25. The Kremlin said on Friday it planned to "exercise all its rights" in the role. The White House urged Russia to "conduct itself professionally" when it assumes the role, saying there was no means to block Moscow from the post. "A country that flagrantly violates the UN Charter and invades its neighbour has no place on the UN Security Council," White House spokesperson Karine Jean-Pierre said on Friday. "Unfortunately, Russia is a permanent member of the Security Council and no feasible international legal pathway exists to change that reality," she added, calling the presidency "a largely ceremonial position". The Baltic states also expressed their concern. Estonia's UN envoy Rein Tammsaar, speaking also on behalf of Latvia and Lithuania, warned the Security Council Friday as it met to discuss Russia's plans to deploy tactical nuclear weapons in neighbouring Belarus. "Isn't it telling that tomorrow, on the anniversary of the Bucha killings, Russia will assume the Presidency of the UN Security Council?

Futurists of the 1990s predicted that we'd be living underwater or riding flying cars by this point -- but now experts are warning of a much scarier future. Other predictions include making contact with aliens -- but whether or not that's a bad thing remains unknown. It's not all doom and gloom, though, with technology expected to have made the afterlife possible. AI'overlords' could turn everyone into serfs Right now, people are focused on AI potentially causing job losses - but the reality could be far worse. That's according to George Stakhov, chief strategy officer for the global ad agency DDB EMEA who created an AI tool named'The Uncreative Agency'.