Automatic spelling correction stands as a pivotal challenge within the ambit of natural language processing (NLP), demanding nuanced solutions. Traditional spelling correction techniques are typically only capable of detecting and correcting non-word errors, such as typos and misspellings. However, context-sensitive errors, also known as real-word errors, are more challenging to detect because they are valid words that are used incorrectly in a given context. The Persian language, characterized by its rich morphology and complex syntax, presents formidable challenges to automatic spelling correction systems. Furthermore, the limited availability of Persian language resources makes it difficult to train effective spelling correction models. This paper introduces a cutting-edge approach for precise and efficient real-word error correction in Persian text. Our methodology adopts a structured, multi-tiered approach, employing semantic analysis, feature selection, and advanced classifiers to enhance error detection and correction efficacy. The innovative architecture discovers and stores semantic similarities between words and phrases in Persian text. The classifiers accurately identify real-word errors, while the semantic ranking algorithm determines the most probable corrections for real-word errors, taking into account specific spelling correction and context properties such as context, semantic similarity, and edit-distance measures. Evaluations have demonstrated that our proposed method surpasses previous Persian real-word error correction models. Our method achieves an impressive F-measure of 96.6% in the detection phase and an accuracy of 99.1% in the correction phase. These results clearly indicate that our approach is a highly promising solution for automatic real-word error correction in Persian text.

Microsoft's global outage has hit vital NHS services, with the medical computer system EMIS not working. The EMIS system is used by GPs to book appointments, view patient notes, order prescriptions and make referrals. However doctors in parts of the UK are currently reporting having a '100 per cent outage' with patients also telling MailOnline they can't get life-saving drugs. Speaking to this website a GP practice manager in Berkshire said: 'We are completely dead in the water. 'We can't see any patients our systems are down.

The Israeli military says it is investigating an apparent drone attack that hit central Tel Aviv in the early hours of Friday. In a statement it said an initial inquiry indicated the explosion had been caused by the falling of an "aerial target" and announced it was increasing air patrols. Israeli emergency services say the explosion left one person dead and several lightly injured. Yemen's Houthi militants, which are backed by Iran, announced on social media that they would reveal details about a military operation that had targeted Tel Aviv. The incident also came after the Israeli military confirmed it had killed a senior commander of the Hezbollah militia in southern Lebanon.

With the advent of foundation models, prompt tuning has positioned itself as an important technique for directing model behaviors and eliciting desired responses. Prompt tuning regards selecting appropriate keywords included into the input, thereby adapting to the downstream task without adjusting or fine-tuning the model parameters. There is a wide range of work in prompt tuning, from approaches that directly harness the backpropagated gradient signals from the model, to those employing black-box optimization such as reinforcement learning (RL) methods. Our primary focus is on RLPrompt, which aims to find optimal prompt tokens leveraging soft Q-learning. While the results show promise, we have observed that the prompts frequently appear unnatural, which impedes their interpretability. We address this limitation by using sparse Tsallis entropy regularization, a principled approach to filtering out unlikely tokens from consideration. We extensively evaluate our approach across various tasks, including few-shot text classification, unsupervised text style transfer, and textual inversion from images. The results indicate a notable improvement over baselines, highlighting the efficacy of our approach in addressing the challenges of prompt tuning. Moreover, we show that the prompts discovered using our method are more natural and interpretable compared to those from other baselines.

The rapid expansion of Artificial Intelligence (AI) technologies has introduced both significant advancements and challenges, with diversity and inclusion (D&I) emerging as a critical concern. Addressing D&I in AI is essential to reduce biases and discrimination, enhance fairness, and prevent adverse societal impacts. Despite its importance, D&I considerations are often overlooked, resulting in incidents marked by built-in biases and ethical dilemmas. Analyzing AI incidents through a D&I lens is crucial for identifying causes of biases and developing strategies to mitigate them, ensuring fairer and more equitable AI technologies. However, systematic investigations of D&I-related AI incidents are scarce. This study addresses these challenges by identifying and understanding D&I issues within AI systems through a manual analysis of AI incident databases (AIID and AIAAIC). The research develops a decision tree to investigate D&I issues tied to AI incidents and populate a public repository of D&I-related AI incidents. The decision tree was validated through a card sorting exercise and focus group discussions. The research demonstrates that almost half of the analyzed AI incidents are related to D&I, with a notable predominance of racial, gender, and age discrimination. The decision tree and resulting public repository aim to foster further research and responsible AI practices, promoting the development of inclusive and equitable AI systems.

Causal inference plays an important role in explanatory analysis and decision making across various fields like statistics, marketing, health care, and education. Its main task is to estimate treatment effects and make intervention policies. Traditionally, most of the previous works typically focus on the binary treatment setting that there is only one treatment for a unit to adopt or not. However, in practice, the treatment can be much more complex, encompassing multi-valued, continuous, or bundle options. In this paper, we refer to these as complex treatments and systematically and comprehensively review the causal inference methods for addressing them. First, we formally revisit the problem definition, the basic assumptions, and their possible variations under specific conditions. Second, we sequentially review the related methods for multi-valued, continuous, and bundled treatment settings. In each situation, we tentatively divide the methods into two categories: those conforming to the unconfoundedness assumption and those violating it. Subsequently, we discuss the available datasets and open-source codes. Finally, we provide a brief summary of these works and suggest potential directions for future research.

This paper presents a novel WiFi-Visual data fusion method for indoor robot (TIAGO++) localization. This method can use 10 WiFi samples and 4 low-resolution images ($58 \times 58$ in pixels) to localize a indoor robot with an average error distance about 1.32 meters. The experiment test is 3 months after the data collection in a general teaching building, whose WiFi and visual environments are partially changed. This indirectly shows the robustness of the proposed method. Instead of neural network design, this paper focuses on the soft data fusion to prevent unbounded errors in visual localization. A double-layer soft data fusion is proposed. The proposed soft data fusion includes the first-layer WiFi-Visual feature fusion and the second-layer decision vector fusion. Firstly, motivated by the excellent capability of neural network in image processing and recognition, the temporal-spatial features are extracted from WiFi data, these features are represented in image form. Secondly, the WiFi temporal-spatial features in image form and the visual features taken by the robot camera are combined together, and are jointly exploited by a classification neural network to produce a likelihood vector for WiFi-Visual localization. This is called first-layer WiFi-Visual fusion. Similarly, these two types of features can exploited separately by neural networks to produce another two independent likelihood vectors. Thirdly, the three likelihood vectors are fused by Hadamard product and median filtering to produce the final likelihood vector for localization. This called the second-layer decision vector fusion. The proposed soft data fusion does not apply any threshold or prioritize any data source over the other in the fusion process. It never excludes the positions of low probabilities, which can avoid the information loss due to a hard decision. The demo video is provided. The code will be open.

In the age of information overload, professionals across various fields face the challenge of navigating vast amounts of documentation and ever-evolving standards. Ensuring compliance with standards, regulations, and contractual obligations is a critical yet complex task across various professional fields. We propose a versatile conversational AI assistant framework designed to facilitate compliance checking on the go, in diverse domains, including but not limited to network infrastructure, legal contracts, educational standards, environmental regulations, and government policies. By leveraging retrieval-augmented generation using large language models, our framework automates the review, indexing, and retrieval of relevant, context-aware information, streamlining the process of verifying adherence to established guidelines and requirements. This AI assistant not only reduces the manual effort involved in compliance checks but also enhances accuracy and efficiency, supporting professionals in maintaining high standards of practice and ensuring regulatory compliance in their respective fields. We propose and demonstrate AuditNet, the first conversational AI security assistant designed to assist IoT network security experts by providing instant access to security standards, policies, and regulations.

Data-to-text (D2T) generation aims to generate human-readable text from semi-structured data, such as tables and graphs. The recent success of D2T is largely attributed to advancements in LLMs. Despite the success of LLMs, no research has been conducted to illustrate the impact of model size on the performance of fine-tuned LLMs for D2T tasks. D2T model performance is typically assessed based on three key qualities: \textit{readability} (indicates fluency and coherence), \textit{informativeness} (measures content similarity), and \textit{faithfulness} (assesses consistency of factual information). It is currently uncertain whether increasing the size of LLMs effectively improves performance in D2T tasks across these three qualities. The objective of this study is to investigate the performance of fine-tuned LLMs in D2T tasks in terms of model size. Through extensive comparative analysis, we aim to elucidate both the advantages and limitations of scaling model sizes across five widely used D2T datasets (E2E, ViGGo, WikiTableText, DART, and WebNLG) and twelve state-of-the-art LLMs with varying sizes from five different LLM families (T5, BART, OPT, BLOOM, and Llama 2). To comprehensively cover all the three essential qualities of D2T models, we incorporate six widely recognized automatic metrics -- \textsc{BLEU}, \textsc{METEOR}, \textsc{BERTScore}, \textsc{MoverScore}, \textsc{Parent}, and \textsc{BARTScore}. We also provide an in-depth analysis of LLM performance concerning model size in the presence of source-reference divergence, a critical aspect of D2T tasks. Our investigation reveals that increasing LLM size enhances \textit{readability} and \textit{informativeness} in D2T tasks, but larger (in terms of size) LLMs may sacrifice \textit{faithfulness}. Moreover, small-sized LLMs show more resilience than larger ones when source-reference divergence is present.

Wrong predictions can lead to various problems in di erent application domains, e.g., improper medical diagnosis [25] and tra c accidents [16]. Enhancing the DL application systems by reducing wrong predictions of DL models in producing outputs is desirable. Studies [9, 51, 52] have shown that DL models are vulnerable to operational input samples that can lead them to produce incorrect predictions in natural scenarios [52], and the prediction con dences of many such failing samples exceed those well-intended guarding con dence levels [54]. For example, strong sunshine may cause the camera of a self-driving car to capture an image full of white pixels, resulting in a prediction failure with high con dence. A major bottleneck in developing DL applications is detecting these overcon dent failures from their deployed DL application systems. To reduce unreliable predictions, many real-world machine-learning-based application systems are equipped with rejectors to discard uncertain decisions [17]. In DL application systems, many existing techniques [6, 17, 45] construct their rejectors for DL models to address the incorrect prediction problem. For example, many recent studies [2, 8, 42, 49] have been conducted to enhance the defense ability of DL models against out-of-distribution (OOD) samples from unknown classes or arti cial examples that are very likely to guide DL models to yield failures.