This chapter focuses on gender-related errors in machine translation (MT) in the context of low-resource languages. We begin by explaining what low-resource languages are, examining the inseparable social and computational factors that create such linguistic hierarchies. We demonstrate through a case study of our mother tongue Bengali, a global language spoken by almost 300 million people but still classified as low-resource, how gender is assumed and inferred in translations to and from the high(est)-resource English when no such information is provided in source texts. We discuss the postcolonial and societal impacts of such errors leading to linguistic erasure and representational harms, and conclude by discussing potential solutions towards uplifting languages by providing them more agency in MT conversations.

Large language models (LLMs) such as GPT-3.5 and CodeLlama are powerful models for code generation and understanding. Fine-tuning these models comes with a high computational cost and requires a large labeled dataset. Alternatively, in-context learning techniques allow models to learn downstream tasks with only a few examples. Recently, researchers have shown how in-context learning performs well in bug detection and repair. In this paper, we propose code-pair classification task in which both the buggy and non-buggy versions are given to the model, and the model identifies the buggy ones. We evaluate our task in real-world dataset of bug detection and two most powerful LLMs. Our experiments indicate that an LLM can often pick the buggy from the non-buggy version of the code, and the code-pair classification task is much easier compared to be given a snippet and deciding if and where a bug exists.

Large-scale graphs with node attributes are increasingly common in various real-world applications. Creating synthetic, attribute-rich graphs that mirror real-world examples is crucial, especially for sharing graph data for analysis and developing learning models when original data is restricted to be shared. Traditional graph generation methods are limited in their capacity to handle these complex structures. Recent advances in diffusion models have shown potential in generating graph structures without attributes and smaller molecular graphs. However, these models face challenges in generating large attributed graphs due to the complex attribute-structure correlations and the large size of these graphs. This paper introduces a novel diffusion model, GraphMaker, specifically designed for generating large attributed graphs. We explore various combinations of node attribute and graph structure generation processes, finding that an asynchronous approach more effectively captures the intricate attribute-structure correlations. We also address scalability issues through edge mini-batching generation. To demonstrate the practicality of our approach in graph data dissemination, we introduce a new evaluation pipeline. The evaluation demonstrates that synthetic graphs generated by GraphMaker can be used to develop competitive graph machine learning models for the tasks defined over the original graphs without actually accessing these graphs, while many leading graph generation methods fall short in this evaluation.

Establishing sound experimental standards and rigour is important in any growing field of research. Deep Multi-Agent Reinforcement Learning (MARL) is one such nascent field. Although exciting progress has been made, MARL has recently come under scrutiny for replicability issues and a lack of standardised evaluation methodology, specifically in the cooperative setting. Although protocols have been proposed to help alleviate the issue, it remains important to actively monitor the health of the field. In this work, we extend the database of evaluation methodology previously published by containing meta-data on MARL publications from top-rated conferences and compare the findings extracted from this updated database to the trends identified in their work. Our analysis shows that many of the worrying trends in performance reporting remain. This includes the omission of uncertainty quantification, not reporting all relevant evaluation details and a narrowing of algorithmic development classes. Promisingly, we do observe a trend towards more difficult scenarios in SMAC-v1, which if continued into SMAC-v2 will encourage novel algorithmic development. Our data indicate that replicability needs to be approached more proactively by the MARL community to ensure trust in the field as we move towards exciting new frontiers.

Meta-learning has emerged as a powerful approach to train neural networks to learn new tasks quickly from limited data. Broad exposure to different tasks leads to versatile representations enabling general problem solving. But, what are the limits of meta-learning? In this work, we explore the potential of amortizing the most powerful universal predictor, namely Solomonoff Induction (SI), into neural networks via leveraging meta-learning to its limits. We use Universal Turing Machines (UTMs) to generate training data used to expose networks to a broad range of patterns. We provide theoretical analysis of the UTM data generation processes and meta-training protocols. We conduct comprehensive experiments with neural architectures (e.g. LSTMs, Transformers) and algorithmic data generators of varying complexity and universality. Our results suggest that UTM data is a valuable resource for meta-learning, and that it can be used to train neural networks capable of learning universal prediction strategies.

This paper presents the first Arabic crossword puzzle generator driven by advanced AI technology. Leveraging cutting-edge large language models including GPT4, GPT3-Davinci, GPT3-Curie, GPT3-Babbage, GPT3-Ada, and BERT, the system generates distinctive and challenging clues. Based on a dataset comprising over 50,000 clue-answer pairs, the generator employs fine-tuning, few/zero-shot learning strategies, and rigorous quality-checking protocols to enforce the generation of high-quality clue-answer pairs. Importantly, educational crosswords contribute to enhancing memory, expanding vocabulary, and promoting problem-solving skills, thereby augmenting the learning experience through a fun and engaging approach, reshaping the landscape of traditional learning methods. The overall system can be exploited as a powerful educational tool that amalgamates AI and innovative learning techniques, heralding a transformative era for Arabic crossword puzzles and the intersection of technology and education.

University students often spend a considerable amount of time seeking answers to common questions from administrators or teachers. This can become tedious for both parties, leading to a need for a solution. In response, this paper proposes a chatbot model that utilizes natural language processing and deep learning techniques to answer frequently asked questions (FAQs) in the Amharic language. Chatbots are computer programs that simulate human conversation through the use of artificial intelligence (AI), acting as a virtual assistant to handle questions and other tasks. The proposed chatbot program employs tokenization, normalization, stop word removal, and stemming to analyze and categorize Amharic input sentences. Three machine learning model algorithms were used to classify tokens and retrieve appropriate responses: Support Vector Machine (SVM), Multinomial Na\"ive Bayes, and deep neural networks implemented through TensorFlow, Keras, and NLTK. The deep learning model achieved the best results with 91.55% accuracy and a validation loss of 0.3548 using an Adam optimizer and SoftMax activation function. The chatbot model was integrated with Facebook Messenger and deployed on a Heroku server for 24-hour accessibility. The experimental results demonstrate that the chatbot framework achieved its objectives and effectively addressed challenges such as Amharic Fidel variation, morphological variation, and lexical gaps. Future research could explore the integration of Amharic WordNet to narrow the lexical gap and support more complex questions.

This survey paper offers a thorough analysis of techniques and algorithms used in the identification of crime leaders within criminal networks. For each technique, the paper examines its effectiveness, limitations, potential for improvement, and future prospects. The main challenge faced by existing survey papers focusing on algorithms for identifying crime leaders and predicting crimes is effectively categorizing these algorithms. To address this limitation, this paper proposes a new methodological taxonomy that hierarchically classifies algorithms into more detailed categories and specific techniques. The paper includes empirical and experimental evaluations to rank the different techniques. The combination of the methodological taxonomy, empirical evaluations, and experimental comparisons allows for a nuanced and comprehensive understanding of the techniques and algorithms for identifying crime leaders, assisting researchers in making informed decisions. Moreover, the paper offers valuable insights into the future prospects of techniques for identifying crime leaders, emphasizing potential advancements and opportunities for further research. Here's an overview of our empirical analysis findings and experimental insights, along with the solution we've devised: (1) PageRank and Eigenvector centrality are reliable for mapping network connections, (2) Katz Centrality can effectively identify influential criminals through indirect links, stressing their significance in criminal networks, (3) current models fail to account for the specific impacts of criminal influence levels, the importance of socio-economic context, and the dynamic nature of criminal networks and hierarchies, and (4) we propose enhancements, such as incorporating temporal dynamics and sentiment analysis to reflect the fluidity of criminal activities and relationships, which could improve the detection of key criminals .

We introduce the spherical convolutional historical simulations coincide with observational measurements, Wasserstein distance to more comprehensively we can compare each model's synthetic climate measure differences between climate models and distribution to the distribution of observational or quasiobservational reanalysis data. This new similarity measure accounts data products (Raäisaänen, 2007), to assess for spatial variability using convolutional their reconstructive skill. For complete spatial coverage we projections and quantifies local differences in the compare against reanalysis data, a blend of observations distribution of climate variables. We apply this and short-range weather forecasts through data assimilation method to evaluate the historical model outputs (Bengtsson et al., 2004). This has become one popular of the Coupled Model Intercomparison Project climate model validation method (Flato et al., 2014).

An adaptive control approach for a three-phase grid-interfaced solar photovoltaic system based on the new Neuro-Fuzzy Inference System with Rain Optimization Algorithm (ANROA) methodology is proposed and discussed in this manuscript. This method incorporates an Adaptive Neuro-fuzzy Inference System (ANFIS) with a Rain Optimization Algorithm (ROA). The ANFIS controller has excellent maximum tracking capability because it includes features of both neural and fuzzy techniques. The ROA technique is in charge of controlling the voltage source converter switching. Avoiding power quality problems including voltage fluctuations, harmonics, and flickers as well as unbalanced loads and reactive power usage is the major goal. Besides, the proposed method performs at zero voltage regulation and unity power factor modes. The suggested control approach has been modeled and simulated, and its performance has been assessed using existing alternative methods. A statistical analysis of proposed and existing techniques has been also presented and discussed. The results of the simulations demonstrate that, when compared to alternative approaches, the suggested strategy may properly and effectively identify the best global solutions. Furthermore, the system's robustness has been studied by using MATLAB/SIMULINK environment and experimentally by Field Programmable Gate Arrays Controller (FPGA)-based Hardware-in-Loop (HLL).