Based on an annotated multimedia corpus, television series Mar{\=a}y{\=a} 2013, we dig into the question of ''automatic standardization'' of Arabic dialects for machine translation. Here we distinguish between rule-based machine translation and statistical machine translation. Machine translation from Arabic most of the time takes standard or modern Arabic as the source language and produces quite satisfactory translations thanks to the availability of the translation memories necessary for training the models. The case is different for the translation of Arabic dialects. The productions are much less efficient. In our research we try to apply machine translation methods to a dialect/standard (or modern) Arabic pair to automatically produce a standard Arabic text from a dialect input, a process we call ''automatic standardization''. we opt here for the application of ''statistical models'' because ''automatic standardization'' based on rules is more hard with the lack of ''diglossic'' dictionaries on the one hand and the difficulty of creating linguistic rules for each dialect on the other. Carrying out this research could then lead to combining ''automatic standardization'' software and automatic translation software so that we take the output of the first software and introduce it as input into the second one to obtain at the end a quality machine translation. This approach may also have educational applications such as the development of applications to help understand different Arabic dialects by transforming dialectal texts into standard Arabic.

While text mining and NLP research has been established for decades, there remain gaps in the literature that reports the use of these techniques in building real-world applications. For example, they typically look at single and sometimes simplified tasks, and do not discuss in-depth data heterogeneity and inconsistency that is common in real-world problems or their implication on the development of their methods. Also, few prior work has focused on the healthcare domain. In this work, we describe an industry project that developed text mining and NLP solutions to mine millions of heterogeneous, multilingual procurement documents in the healthcare sector. We extract structured procurement contract data that is used to power a platform for dynamically assessing supplier risks. Our work makes unique contributions in a number of ways. First, we deal with highly heterogeneous, multilingual data and we document our approach to tackle these challenges. This is mainly based on a method that effectively uses domain knowledge and generalises to multiple text mining and NLP tasks and languages. Second, applying this method to mine millions of procurement documents, we develop the first structured procurement contract database that will help facilitate the tendering process. Second, Finally, we discuss lessons learned for practical text mining/NLP development, and make recommendations for future research and practice.

Federated Machine Learning (Fed ML) is a new distributed machine learning technique applied to collaboratively train a global model using clients local data without transmitting it. Nodes only send parameter updates (e.g., weight updates in the case of neural networks), which are fused together by the server to build the global model. By not divulging node data, Fed ML guarantees its confidentiality, a crucial aspect of network security, which enables it to be used in the context of data-sensitive Internet of Things (IoT) and mobile applications, such as smart Geo-location and the smart grid. However, most IoT devices are particularly energy constrained, which raises the need to optimize the Fed ML process for efficient training tasks and optimized power consumption. In this paper, we conduct, to the best of our knowledge, the first Systematic Mapping Study (SMS) on Fed ML optimization techniques for energy-constrained IoT devices. From a total of more than 800 papers, we select 67 that satisfy our criteria and give a structured overview of the field using a set of carefully chosen research questions. Finally, we attempt to provide an analysis of the energy-constrained Fed ML state of the art and try to outline some potential recommendations for the research community.

We propose a Bayesian tensor regression model to accommodate the effect of multiple factors on phenotype prediction. We adopt a set of prior distributions that resolve identifiability issues that may arise between the parameters in the model. Simulation experiments show that our method out-performs previous related models and machine learning algorithms under different sample sizes and degrees of complexity. We further explore the applicability of our model by analysing real-world data related to wheat production across Ireland from 2010 to 2019. Our model performs competitively and overcomes key limitations found in other analogous approaches. Finally, we adapt a set of visualisations for the posterior distribution of the tensor effects that facilitate the identification of optimal interactions between the tensor variables whilst accounting for the uncertainty in the posterior distribution.

Representation learning is the foundation of natural language processing (NLP). This work presents new methods to employ visual information as assistant signals to general NLP tasks. For each sentence, we first retrieve a flexible number of images either from a light topic-image lookup table extracted over the existing sentence-image pairs or a shared cross-modal embedding space that is pre-trained on out-of-shelf text-image pairs. Then, the text and images are encoded by a Transformer encoder and convolutional neural network, respectively. The two sequences of representations are further fused by an attention layer for the interaction of the two modalities. In this study, the retrieval process is controllable and flexible. The universal visual representation overcomes the lack of large-scale bilingual sentence-image pairs. Our method can be easily applied to text-only tasks without manually annotated multimodal parallel corpora. We apply the proposed method to a wide range of natural language generation and understanding tasks, including neural machine translation, natural language inference, and semantic similarity. Experimental results show that our method is generally effective for different tasks and languages. Analysis indicates that the visual signals enrich textual representations of content words, provide fine-grained grounding information about the relationship between concepts and events, and potentially conduce to disambiguation.

Recent work on unsupervised speech segmentation has used self-supervised models with phone and word segmentation modules that are trained jointly. This paper instead revisits an older approach to word segmentation: bottom-up phone-like unit discovery is performed first, and symbolic word segmentation is then performed on top of the discovered units (without influencing the lower level). To do this, I propose a new unit discovery model, a new symbolic word segmentation model, and then chain the two models to segment speech. Both models use dynamic programming to minimize segment costs from a self-supervised network with an additional duration penalty that encourages longer units. Concretely, for acoustic unit discovery, duration-penalized dynamic programming (DPDP) is used with a contrastive predictive coding model as the scoring network. For word segmentation, DPDP is applied with an autoencoding recurrent neural as the scoring network. The two models are chained in order to segment speech. This approach gives comparable word segmentation results to state-of-the-art joint self-supervised segmentation models on an English benchmark. On French, Mandarin, German and Wolof data, it outperforms previous systems on the ZeroSpeech benchmarks. Analysis shows that the chained DPDP system segments shorter filler words well, but longer words might require some external top-down signal.

The ability to generalise well is one of the primary desiderata of natural language processing (NLP). Yet, what 'good generalisation' entails and how it should be evaluated is not well understood, nor are there any evaluation standards for generalisation. In this paper, we lay the groundwork to address both of these issues. We present a taxonomy for characterising and understanding generalisation research in NLP. Our taxonomy is based on an extensive literature review of generalisation research, and contains five axes along which studies can differ: their main motivation, the type of generalisation they investigate, the type of data shift they consider, the source of this data shift, and the locus of the shift within the modelling pipeline. We use our taxonomy to classify over 400 papers that test generalisation, for a total of more than 600 individual experiments. Considering the results of this review, we present an in-depth analysis that maps out the current state of generalisation research in NLP, and we make recommendations for which areas might deserve attention in the future. Along with this paper, we release a webpage where the results of our review can be dynamically explored, and which we intend to update as new NLP generalisation studies are published. With this work, we aim to take steps towards making state-of-the-art generalisation testing the new status quo in NLP.

The study of zero-shot generalisation (ZSG) in deep Reinforcement Learning (RL) aims to produce RL algorithms whose policies generalise well to novel unseen situations at deployment time, avoiding overfitting to their training environments. Tackling this is vital if we are to deploy reinforcement learning algorithms in real world scenarios, where the environment will be diverse, dynamic and unpredictable. This survey is an overview of this nascent field. We rely on a unifying formalism and terminology for discussing different ZSG problems, building upon previous works. We go on to categorise existing benchmarks for ZSG, as well as current methods for tackling these problems. Finally, we provide a critical discussion of the current state of the field, including recommendations for future work. Among other conclusions, we argue that taking a purely procedural content generation approach to benchmark design is not conducive to progress in ZSG, we suggest fast online adaptation and tackling RL-specific problems as some areas for future work on methods for ZSG, and we recommend building benchmarks in underexplored problem settings such as offline RL ZSG and reward-function variation.

For every machine learning enthusiast, we were told to go to Kaggle. Should it end at just making predictions on the test data and submitting it? Or we would always be supplied with excel sheets to make predictions on with the model in real-life scenarios. What do we need to do? Read along to find out what needs to be done. Kowepe bank of Nigeria conducted marketing campaigns via phone calls with their clients. These campaigns prompt their clients to subscribe to a specific financial product of the bank (term deposit).

A major focus of Computer Weekly's technology and ethics coverage in 2022 was on working conditions throughout the tech sector, from the issue of forced labour and slavery throughout technology supply chains, to UK Amazon workers staging spontaneous "wildcat" strikes in response to derisory pay rises and warehouse conditions. Other stories in this vein included coverage of accusations that "soft union-busting" tactics were used by app-based food delivery firm Deliveroo to scupper its workers' grassroots organising efforts, and the ongoing court case against five major tech firms for their alleged role in the maiming and deaths of people extracting raw materials in the Democratic Republic of Congo. Artificial intelligence (AI) also featured heavily in Computer Weekly's technology and ethics coverage in 2022, with stories published on the tech sector's lacklustre commitment to "ethical" AI, as well as on the pitfalls and challenges of auditing AI-powered algorithms. Police technology was another major focus of 2022, as policing bodies continue to push ahead with new tech deployments such as live facial recognition (LFR) despite serious concerns about its effectiveness, proportionality and efficacy. Other stories focused on how technology is developed and deployed, and the underlying power dynamics at play.