Information Retrieval (IR) constitutes a vital facet of Open Domain Question Answering (ODQA) systems, focusing on the exploration of pertinent information within extensive collections of passages, such as Wikipedia, to facilitate subsequent reader processing. Historically, IR relied on textual overlaps for relevant context retrieval, employing methods like BM25 and TF-IDF, which, however, lacked natural language understanding. The advent of deep learning ushered in a new era, leading to the introduction of Dense Passage Retrievers (DPR), shows superiority over traditional sparse retrievers. These dense retrievers leverage Pre-Trained Language Models (PLMs) to initialize context encoders, enabling the extraction of natural language representations. They utilize the distance between latent vectors of contexts as a metric for assessing similarity. However, DPR methods are heavily reliant on large volumes of meticulously labeled data, such as Natural Questions. The process of data labeling is both costly and time-intensive. In this article, we propose a novel data augmentation methodology Self Data Augmentation (SDA) that employs DPR models to automatically annotate unanswered questions. Specifically, we initiate the process by retrieving relevant pseudo passages for these unlabeled questions. We subsequently introduce three distinct passage selection methods to annotate these pseudo passages. Ultimately, we amalgamate the pseudo-labeled passages with the unanswered questions to create augmented data. Our experimental evaluations conducted on two extensive datasets (Natural Questions and TriviaQA), alongside a relatively small dataset (WebQuestions), utilizing three diverse base models, illustrate the significant enhancement achieved through the incorporation of freshly augmented data. Moreover, our proposed data augmentation method exhibits remarkable flexibility, which is readily adaptable to various dense retrievers. Additionally, we have conducted a comprehensive human study on the augmented data, which further supports our conclusions.

In traditional machine learning, classifiers training is typically undertaken in the setting of single-task learning, so the trained classifier can discriminate between different classes. However, this must be based on the assumption that different classes are mutually exclusive. In real applications, the above assumption does not always hold. For example, the same book may belong to multiple subjects. From this point of view, researchers were motivated to formulate multi-label learning problems. In this context, each instance can be assigned multiple labels but the classifiers training is still typically undertaken in the setting of single-task learning. When probabilistic approaches are adopted for classifiers training, multi-task learning can be enabled through transformation of a multi-labelled data set into several binary data sets. The above data transformation could usually result in the class imbalance issue. Without the above data transformation, multi-labelling of data results in an exponential increase of the number of classes, leading to fewer instances for each class and a higher difficulty for identifying each class. In addition, multi-labelling of data is very time consuming and expensive in some application areas, such as hate speech detection. In this paper, we introduce a novel formulation of the hate speech type identification problem in the setting of multi-task learning through our proposed fuzzy ensemble approach. In this setting, single-labelled data can be used for semi-supervised multi-label learning and two new metrics (detection rate and irrelevance rate) are thus proposed to measure more effectively the performance for this kind of learning tasks. We report an experimental study on identification of four types of hate speech, namely: religion, race, disability and sexual orientation. The experimental results show that our proposed fuzzy ensemble approach outperforms other popular probabilistic approaches, with an overall detection rate of 0.93.

Offensive or antagonistic language targeted at individuals and social groups based on their personal characteristics (also known as cyber hate speech or cyberhate) has been frequently posted and widely circulated via the World Wide Web. This can be considered as a key risk factor for individual and societal tension surrounding regional instability. Automated Web-based cyberhate detection is important for observing and understanding community and regional societal tension—especially in online social networks where posts can be rapidly and widely viewed and disseminated. While previous work has involved using lexicons, bags-of-words, or probabilistic language parsing approaches, they often suffer from a similar issue, which is that cyberhate can be subtle and indirect—thus, depending on the occurrence of individual words or phrases, can lead to a significant number of false negatives, providing inaccurate representation of the trends in cyberhate. This problem motivated us to challenge thinking around the representation of subtle language use, such as references to perceived threats from “the other” including immigration or job prosperity in a hateful context. We propose a novel “othering” feature set that utilizes language use around the concept of “othering” and intergroup threat theory to identify these subtleties, and we implement a wide range of classification methods using embedding learning to compute semantic distances between parts of speech considered to be part of an “othering” narrative. To validate our approach, we conducted two sets of experiments. The first involved comparing the results of our novel method with state-of-the-art baseline models from the literature. Our approach outperformed all existing methods. The second tested the best performing models from the first phase on unseen datasets for different types of cyberhate, namely religion, disability, race, and sexual orientation. The results showed F-measure scores for classifying hateful instances obtained through applying our model of 0.81, 0.71, 0.89, and 0.72, respectively, demonstrating the ability of the “othering” narrative to be an important part of model generalization.