Anomaly detection is widely used in a broad range of domains from cybersecurity to manufacturing, finance, and so on. Deep learning based anomaly detection has recently drawn much attention because of its superior capability of recognizing complex data patterns and identifying outliers accurately. However, deep learning models are typically iteratively optimized in a central server with input data gathered from edge devices, and such data transfer between edge devices and the central server impose substantial overhead on the network and incur additional latency and energy consumption. To overcome this problem, we propose a fully-automated, lightweight, statistical learning based anomaly detection framework called LightESD. It is an on-device learning method without the need for data transfer between edge and server, and is extremely lightweight that most low-end edge devices can easily afford with negligible delay, CPU/memory utilization, and power consumption. Yet, it achieves highly competitive detection accuracy. Another salient feature is that it can auto-adapt to probably any dataset without manually setting or configuring model parameters or hyperparameters, which is a drawback of most existing methods. We focus on time series data due to its pervasiveness in edge applications such as IoT. Our evaluation demonstrates that LightESD outperforms other SOTA methods on detection accuracy, efficiency, and resource consumption. Additionally, its fully automated feature gives it another competitive advantage in terms of practical usability and generalizability.

Fine-grained entity typing (FET), which assigns entities in text with context-sensitive, fine-grained semantic types, will play an important role in natural language understanding. A supervised FET method, which typically relies on human-annotated corpora for training, is costly and difficult to scale. Recent studies leverage pre-trained language models (PLMs) to generate rich and context-aware weak supervision for FET. However, a PLM may still generate a mixture of rough and fine-grained types, or tokens unsuitable for typing. In this study, we vision that an ontology provides a semantics-rich, hierarchical structure, which will help select the best results generated by multiple PLM models and head words. Specifically, we propose a novel zero-shot, ontology-guided FET method, OntoType, which follows a type ontological structure, from coarse to fine, ensembles multiple PLM prompting results to generate a set of type candidates, and refines its type resolution, under the local context with a natural language inference model. Our experiments on the Ontonotes, FIGER, and NYT datasets using their associated ontological structures demonstrate that our method outperforms the state-of-the-art zero-shot fine-grained entity typing methods. Our error analysis shows that refinement of the existing ontology structures will further improve fine-grained entity typing.

Real-time perception, or streaming perception, is a crucial aspect of autonomous driving that has yet to be thoroughly explored in existing research. To address this gap, we present DAMO-StreamNet, an optimized framework that combines recent advances from the YOLO series with a comprehensive analysis of spatial and temporal perception mechanisms, delivering a cutting-edge solution. The key innovations of DAMO-StreamNet are (1) A robust neck structure incorporating deformable convolution, enhancing the receptive field and feature alignment capabilities (2) A dual-branch structure that integrates short-path semantic features and long-path temporal features, improving motion state prediction accuracy. (3) Logits-level distillation for efficient optimization, aligning the logits of teacher and student networks in semantic space. (4) A real-time forecasting mechanism that updates support frame features with the current frame, ensuring seamless streaming perception during inference. Our experiments demonstrate that DAMO-StreamNet surpasses existing state-of-the-art methods, achieving 37.8% (normal size (600, 960)) and 43.3% (large size (1200, 1920)) sAP without using extra data. This work not only sets a new benchmark for real-time perception but also provides valuable insights for future research. Additionally, DAMO-StreamNet can be applied to various autonomous systems, such as drones and robots, paving the way for real-time perception. The code is at https://github.com/zhiqic/DAMO-StreamNet.

Ensembling BERT models often significantly improves accuracy, but at the cost of significantly more computation and memory footprint. In this work, we propose Multi-CLS BERT, a novel ensembling method for CLS-based prediction tasks that is almost as efficient as a single BERT model. Multi-CLS BERT uses multiple CLS tokens with a parameterization and objective that encourages their diversity. Thus instead of fine-tuning each BERT model in an ensemble (and running them all at test time), we need only fine-tune our single Multi-CLS BERT model (and run the one model at test time, ensembling just the multiple final CLS embeddings). To test its effectiveness, we build Multi-CLS BERT on top of a state-of-the-art pretraining method for BERT (Aroca-Ouellette and Rudzicz, 2020). In experiments on GLUE and SuperGLUE we show that our Multi-CLS BERT reliably improves both overall accuracy and confidence estimation. When only 100 training samples are available in GLUE, the Multi-CLS BERT_Base model can even outperform the corresponding BERT_Large model. We analyze the behavior of our Multi-CLS BERT, showing that it has many of the same characteristics and behavior as a typical BERT 5-way ensemble, but with nearly 4-times less computation and memory.

This paper argues that Machine Learning (ML) algorithms must be educated. ML-trained algorithms' moral decisions are ubiquitous in human society. Sometimes reverting the societal advances governments, NGOs and civil society have achieved with great effort in the last decades or are yet on the path to be achieved. While their decisions have an incommensurable impact on human societies, these algorithms are within the least educated agents known (data incomplete, un-inclusive, or biased). ML algorithms are not something separate from our human idiosyncrasy but an enactment of our most implicit prejudices and biases. Some research is devoted to "responsibility assignment" as a strategy to tackle immoral AI behaviour. Yet this paper argues that the solution for AI ethical decision-making resides in algorithm education" (as opposed to the "training") of ML. Drawing from an analogy between ML and child education for social responsibility, the paper offers clear directions for responsible and sustainable AI design, specifically with respect to how to educate algorithms to decide ethically.

The VNHSGE (VietNamese High School Graduation Examination) dataset, developed exclusively for evaluating large language models (LLMs), is introduced in this article. The dataset, which covers nine subjects, was generated from the Vietnamese National High School Graduation Examination and comparable tests. 300 literary essays have been included, and there are over 19,000 multiple-choice questions on a range of topics. The dataset assesses LLMs in multitasking situations such as question answering, text generation, reading comprehension, visual question answering, and more by including both textual data and accompanying images. Using ChatGPT and BingChat, we evaluated LLMs on the VNHSGE dataset and contrasted their performance with that of Vietnamese students to see how well they performed. The results show that ChatGPT and BingChat both perform at a human level in a number of areas, including literature, English, history, geography, and civics education. They still have space to grow, though, especially in the areas of mathematics, physics, chemistry, and biology. The VNHSGE dataset seeks to provide an adequate benchmark for assessing the abilities of LLMs with its wide-ranging coverage and variety of activities. We intend to promote future developments in the creation of LLMs by making this dataset available to the scientific community, especially in resolving LLMs' limits in disciplines involving mathematics and the natural sciences.

After introducing the scope of this paper, we start by discussing what an "explanation" really is. We then move on to discuss some of the existing approaches to XAI and build a taxonomy of the most popular methods. Next, we also look at a few applications of these and other XAI techniques in four primary domains: finance, autonomous driving, healthcare and manufacturing. We end by introducing a promising discipline, "Explanation Engineering," which includes a systematic approach for designing explainability into AI systems.

The public sector faces several challenges, such as a number of external and internal demands for change, citizens' dissatisfaction and frustration with public sector organizations, that need to be addressed. An alternative to the traditional top-down development of public services is co-creation of public services. Co-creation promotes collaboration between stakeholders with the aim to create better public services and achieve public values. At the same time, data analytics has been fuelled by the availability of immense amounts of textual data. Whilst both co-creation and TA have been used in the private sector, we study existing works on the application of Text Analytics (TA) techniques on text data to support public service co-creation. We systematically review 75 of the 979 papers that focus directly or indirectly on the application of TA in the context of public service development. In our review, we analyze the TA techniques, the public service they support, public value outcomes, and the co-creation phase they are used in. Our findings indicate that the TA implementation for co-creation is still in its early stages and thus still limited. Our research framework promotes the concept and stimulates the strengthening of the role of Text Analytics techniques to support public sector organisations and their use of co-creation process. From policy-makers' and public administration managers' standpoints, our findings and the proposed research framework can be used as a guideline in developing a strategy for the designing co-created and user-centred public services.

Objective: Evictions are important social and behavioral determinants of health. Evictions are associated with a cascade of negative events that can lead to unemployment, housing insecurity/homelessness, long-term poverty, and mental health problems. In this study, we developed a natural language processing system to automatically detect eviction status from electronic health record (EHR) notes. Materials and Methods: We first defined eviction status (eviction presence and eviction period) and then annotated eviction status in 5000 EHR notes from the Veterans Health Administration (VHA). We developed a novel model, KIRESH, that has shown to substantially outperform other state-of-the-art models such as fine-tuning pre-trained language models like BioBERT and BioClinicalBERT. Moreover, we designed a novel prompt to further improve the model performance by using the intrinsic connection between the two sub-tasks of eviction presence and period prediction. Finally, we used the Temperature Scaling-based Calibration on our KIRESH-Prompt method to avoid over-confidence issues arising from the imbalance dataset. Results: KIRESH-Prompt substantially outperformed strong baseline models including fine-tuning the BioClinicalBERT model to achieve 0.74672 MCC, 0.71153 Macro-F1, and 0.83396 Micro-F1 in predicting eviction period and 0.66827 MCC, 0.62734 Macro-F1, and 0.7863 Micro-F1 in predicting eviction presence. We also conducted additional experiments on a benchmark social determinants of health (SBDH) dataset to demonstrate the generalizability of our methods. Conclusion and Future Work: KIRESH-Prompt has substantially improved eviction status classification. We plan to deploy KIRESH-Prompt to the VHA EHRs as an eviction surveillance system to help address the US Veterans' housing insecurity.

Russia unleashed another widespread missile and drone attack overnight on cities across Ukraine, including targeting the capital, Kyiv, for the 10th time this month, Ukrainian officials said on Friday. At least three cruise missiles and six attack drones managed to evade air defenses, according to Ukraine's Air Force. There was no immediate information on casualties or what was hit. The air force said in a statement that three cruise missiles and 16 Iranian-made Shahed-136 drones had been intercepted, and local officials in Lviv said that five of those were over their region, in western Ukraine. The attack drones came in "several waves" with short intervals in between, according to the city's military administration, which said all had been shot down.