Despite recent advancements, NLP models continue to be vulnerable to bias. This bias often originates from the uneven distribution of real-world data and can propagate through the annotation process. Escalated integration of these models in our lives calls for methods to mitigate bias without overbearing annotation costs. While active learning (AL) has shown promise in training models with a small amount of annotated data, AL's reliance on the model's behavior for selective sampling can lead to an accumulation of unwanted bias rather than bias mitigation. However, infusing clustering with AL can overcome the bias issue of both AL and traditional annotation methods while exploiting AL's annotation efficiency. In this paper, we propose a novel adaptive clustering-based active learning algorithm, D-CALM, that dynamically adjusts clustering and annotation efforts in response to an estimated classifier error-rate. Experiments on eight datasets for a diverse set of text classification tasks, including emotion, hatespeech, dialog act, and book type detection, demonstrate that our proposed algorithm significantly outperforms baseline AL approaches with both pretrained transformers and traditional Support Vector Machines. D-CALM showcases robustness against different measures of information gain and, as evident from our analysis of label and error distribution, can significantly reduce unwanted model bias.

Fetal health is a critical concern during pregnancy as it can impact the well-being of both the mother and the baby. Regular monitoring and timely interventions are necessary to ensure the best possible outcomes. While there are various methods to monitor fetal health in the mother's womb, the use of artificial intelligence (AI) can improve the accuracy, efficiency, and speed of diagnosis. In this study, we propose a robust ensemble model called ensemble of tuned Support Vector Machine and ExtraTrees (ETSE) for predicting fetal health. Initially, we employed various data preprocessing techniques such as outlier rejection, missing value imputation, data standardization, and data sampling. Then, seven machine learning (ML) classifiers including Support Vector Machine (SVM), XGBoost (XGB), Light Gradient Boosting Machine (LGBM), Decision Tree (DT), Random Forest (RF), ExtraTrees (ET), and K-Neighbors were implemented. These models were evaluated and then optimized by hyperparameter tuning using the grid search technique. Finally, we analyzed the performance of our proposed ETSE model. The performance analysis of each model revealed that our proposed ETSE model outperformed the other models with 100% precision, 100% recall, 100% F1-score, and 99.66% accuracy. This indicates that the ETSE model can effectively predict fetal health, which can aid in timely interventions and improve outcomes for both the mother and the baby.

The robustness of a model for real-world deployment is decided by how well it performs on unseen data and distinguishes between in-domain and out-of-domain samples. Visual document classifiers have shown impressive performance on in-distribution test sets. However, they tend to have a hard time correctly classifying and differentiating out-of-distribution examples. Image-based classifiers lack the text component, whereas multi-modality transformer-based models face the token serialization problem in visual documents due to their diverse layouts. They also require a lot of computing power during inference, making them impractical for many real-world applications. We propose, GVdoc, a graph-based document classification model that addresses both of these challenges. Our approach generates a document graph based on its layout, and then trains a graph neural network to learn node and graph embeddings. Through experiments, we show that our model, even with fewer parameters, outperforms state-of-the-art models on out-of-distribution data while retaining comparable performance on the in-distribution test set.

NLP models often degrade in performance when real world data distributions differ markedly from training data. However, existing dataset drift metrics in NLP have generally not considered specific dimensions of linguistic drift that affect model performance, and they have not been validated in their ability to predict model performance at the individual example level, where such metrics are often used in practice. In this paper, we propose three dimensions of linguistic dataset drift: vocabulary, structural, and semantic drift. These dimensions correspond to content word frequency divergences, syntactic divergences, and meaning changes not captured by word frequencies (e.g. lexical semantic change). We propose interpretable metrics for all three drift dimensions, and we modify past performance prediction methods to predict model performance at both the example and dataset level for English sentiment classification and natural language inference. We find that our drift metrics are more effective than previous metrics at predicting out-of-domain model accuracies (mean 16.8% root mean square error decrease), particularly when compared to popular fine-tuned embedding distances (mean 47.7% error decrease). Fine-tuned embedding distances are much more effective at ranking individual examples by expected performance, but decomposing into vocabulary, structural, and semantic drift produces the best example rankings of all considered model-agnostic drift metrics (mean 6.7% ROC AUC increase).

In the end-of-line test of geared motors, the evaluation of product qual-ity is important. Due to time constraints and the high diversity of variants, acous-tic measurements are more economical than vibration measurements. However, the acoustic data is affected by industrial disturbing noise. Therefore, the aim of this study is to investigate the robustness of features used for anomaly detection in geared motor end-of-line testing. A real-world dataset with typical faults and acoustic disturbances is recorded by an acoustic array. This includes industrial noise from the production and systematically produced disturbances, used to compare the robustness. Overall, it is proposed to apply features extracted from a log-envelope spectrum together with psychoacoustic features. The anomaly de-tection is done by using the isolation forest or the more universal bagging random miner. Most disturbances can be circumvented, while the use of a hammer or air pressure often causes problems. In general, these results are important for condi-tion monitoring tasks that are based on acoustic or vibration measurements. Fur-thermore, a real-world problem description is presented to improve common sig-nal processing and machine learning tasks.

Code generation from text requires understanding the user's intent from a natural language description and generating an executable code snippet that satisfies this intent. While recent pretrained language models demonstrate remarkable performance for this task, these models fail when the given natural language description is under-specified. In this work, we introduce a novel and more realistic setup for this task. We hypothesize that the under-specification of a natural language description can be resolved by asking clarification questions. Therefore, we collect and introduce a new dataset named CodeClarQA containing pairs of natural language descriptions and code with created synthetic clarification questions and answers. The empirical results of our evaluation of pretrained language model performance on code generation show that clarifications result in more precisely generated code, as shown by the substantial improvement of model performance in all evaluation metrics. Alongside this, our task and dataset introduce new challenges to the community, including when and what clarification questions should be asked. Our code and dataset are available on GitHub.

Adversarial attacks represent a security threat to machine learning based automatic speech recognition (ASR) systems. To prevent such attacks we propose an adversarial example detection strategy applicable to any ASR system that predicts a probability distribution over output tokens in each time step. We measure a set of characteristics of this distribution: the median, maximum, and minimum over the output probabilities, the entropy, and the Jensen-Shannon divergence of the distributions of subsequent time steps. Then, we fit a Gaussian distribution to the characteristics observed for benign data. By computing the likelihood of incoming new audio we can distinguish malicious inputs from samples from clean data with an area under the receiving operator characteristic (AUROC) higher than 0.99, which drops to 0.98 for less-quality audio. To assess the robustness of our method we build adaptive attacks. This reduces the AUROC to 0.96 but results in more noisy adversarial clips.

Marine animals and deep underwater objects are difficult to recognize and monitor for safety of aquatic life. There is an increasing challenge when the water is saline with granular particles and impurities. In such natural adversarial environment, traditional approaches like CNN start to fail and are expensive to compute. This project involves implementing and evaluating various object detection models, including EfficientDet, YOLOv5, YOLOv8, and Detectron2, on an existing annotated underwater dataset, called the Brackish-Dataset. The dataset comprises annotated image sequences of fish, crabs, starfish, and other aquatic animals captured in Limfjorden water with limited visibility. The aim of this research project is to study the efficiency of newer models on the same dataset and contrast them with the previous results based on accuracy and inference time. Firstly, I compare the results of YOLOv3 (31.10% mean Average Precision (mAP)), YOLOv4 (83.72% mAP), YOLOv5 (97.6%), YOLOv8 (98.20%), EfficientDet (98.56% mAP) and Detectron2 (95.20% mAP) on the same dataset. Secondly, I provide a modified BiSkFPN mechanism (BiFPN neck with skip connections) to perform complex feature fusion in adversarial noise which makes modified EfficientDet robust to perturbations. Third, analyzed the effect on accuracy of EfficientDet (98.63% mAP) and YOLOv5 by adversarial learning (98.04% mAP). Last, I provide class activation map based explanations (CAM) for the two models to promote Explainability in black box models. Overall, the results indicate that modified EfficientDet achieved higher accuracy with five-fold cross validation than the other models with 88.54% IoU of feature maps.

Multi-view datasets offer diverse forms of data that can enhance prediction models by providing complementary information. However, the use of multi-view data leads to an increase in high-dimensional data, which poses significant challenges for the prediction models that can lead to poor generalization. Therefore, relevant feature selection from multi-view datasets is important as it not only addresses the poor generalization but also enhances the interpretability of the models. Despite the success of traditional feature selection methods, they have limitations in leveraging intrinsic information across modalities, lacking generalizability, and being tailored to specific classification tasks. We propose a novel genetic algorithm strategy to overcome these limitations of traditional feature selection methods for multi-view data. Our proposed approach, called the multi-view multi-objective feature selection genetic algorithm (MMFS-GA), simultaneously selects the optimal subset of features within a view and between views under a unified framework. The MMFS-GA framework demonstrates superior performance and interpretability for feature selection on multi-view datasets in both binary and multiclass classification tasks. The results of our evaluations on three benchmark datasets, including synthetic and real data, show improvement over the best baseline methods. This work provides a promising solution for multi-view feature selection and opens up new possibilities for further research in multi-view datasets.

During crisis situations, social media allows people to quickly share information, including messages requesting help. This can be valuable to emergency responders, who need to categorise and prioritise these messages based on the type of assistance being requested. However, the high volume of messages makes it difficult to filter and prioritise them without the use of computational techniques. Fully supervised filtering techniques for crisis message categorisation typically require a large amount of annotated training data, but this can be difficult to obtain during an ongoing crisis and is expensive in terms of time and labour to create. This thesis focuses on addressing the challenge of low data availability when categorising crisis messages for emergency response. It first presents domain adaptation as a solution for this problem, which involves learning a categorisation model from annotated data from past crisis events (source domain) and adapting it to categorise messages from an ongoing crisis event (target domain). In many-to-many adaptation, where the model is trained on multiple past events and adapted to multiple ongoing events, a multi-task learning approach is proposed using pre-trained language models. This approach outperforms baselines and an ensemble approach further improves performance...