Unsupervised commonsense question answering requires mining effective commonsense knowledge without the rely on the labeled task data. Previous methods typically retrieved from traditional knowledge bases or used pre-trained language models (PrLMs) to generate fixed types of knowledge, which have poor generalization ability. In this paper, we aim to address the above limitation by leveraging the implicit knowledge stored in PrLMs and propose a two-stage prompt-based unsupervised commonsense question answering framework (TSGP). Specifically, we first use knowledge generation prompts to generate the knowledge required for questions with unlimited types and possible candidate answers independent of specified choices. Then, we further utilize answer generation prompts to generate possible candidate answers independent of specified choices. Experimental results and analysis on three different commonsense reasoning tasks, CommonsenseQA, OpenBookQA, and SocialIQA, demonstrate that TSGP significantly improves the reasoning ability of language models in unsupervised settings. Our code is available at: https://github.com/Yueqing-Sun/TSGP.

This paper investigates a new yet challenging problem called Reverse $k$-Maximum Inner Product Search (R$k$MIPS). Given a query (item) vector, a set of item vectors, and a set of user vectors, the problem of R$k$MIPS aims to find a set of user vectors whose inner products with the query vector are one of the $k$ largest among the query and item vectors. We propose the first subquadratic-time algorithm, i.e., Shifting-aware Asymmetric Hashing (SAH), to tackle the R$k$MIPS problem. To speed up the Maximum Inner Product Search (MIPS) on item vectors, we design a shifting-invariant asymmetric transformation and develop a novel sublinear-time Shifting-Aware Asymmetric Locality Sensitive Hashing (SA-ALSH) scheme. Furthermore, we devise a new blocking strategy based on the Cone-Tree to effectively prune user vectors (in a batch). We prove that SAH achieves a theoretical guarantee for solving the RMIPS problem. Experimental results on five real-world datasets show that SAH runs 4$\sim$8$\times$ faster than the state-of-the-art methods for R$k$MIPS while achieving F1-scores of over 90\%. The code is available at \url{https://github.com/HuangQiang/SAH}.

In recent years, multilingual pre-trained language models have gained prominence due to their remarkable performance on numerous downstream Natural Language Processing tasks (NLP). However, pre-training these large multilingual language models requires a lot of training data, which is not available for African Languages. Active learning is a semi-supervised learning algorithm, in which a model consistently and dynamically learns to identify the most beneficial samples to train itself on, in order to achieve better optimization and performance on downstream tasks. Furthermore, active learning effectively and practically addresses real-world data scarcity. Despite all its benefits, active learning, in the context of NLP and especially multilingual language models pretraining, has received little consideration. In this paper, we present AfroLM, a multilingual language model pretrained from scratch on 23 African languages (the largest effort to date) using our novel self-active learning framework. Pretrained on a dataset significantly (14x) smaller than existing baselines, AfroLM outperforms many multilingual pretrained language models (AfriBERTa, XLMR-base, mBERT) on various NLP downstream tasks (NER, text classification, and sentiment analysis). Additional out-of-domain sentiment analysis experiments show that \textbf{AfroLM} is able to generalize well across various domains. We release the code source, and our datasets used in our framework at https://github.com/bonaventuredossou/MLM_AL.

The 21 cm spectral line emission of atomic neutral hydrogen (HI) is one of the primary wavelengths observed in radio astronomy. However, the signal is intrinsically faint and the HI content of galaxies depends on the cosmic environment, requiring large survey volumes and survey depth to investigate the HI Universe. As the amount of data coming from these surveys continues to increase with technological improvements, so does the need for automatic techniques for identifying and characterising HI sources while considering the tradeoff between completeness and purity. This study aimed to find the optimal pipeline for finding and masking the most sources with the best mask quality and the fewest artefacts in 3D neutral hydrogen cubes. Various existing methods were explored in an attempt to create a pipeline to optimally identify and mask the sources in 3D neutral hydrogen 21 cm spectral line data cubes. Two traditional source-finding methods were tested, SoFiA and MTObjects, as well as a new supervised deep learning approach, in which a 3D convolutional neural network architecture, known as V-Net was used. These three source-finding methods were further improved by adding a classical machine learning classifier as a post-processing step to remove false positive detections. The pipelines were tested on HI data cubes from the Westerbork Synthesis Radio Telescope with additional inserted mock galaxies. SoFiA combined with a random forest classifier provided the best results, with the V-Net-random forest combination a close second. We suspect this is due to the fact that there are many more mock sources in the training set than real sources. There is, therefore, room to improve the quality of the V-Net network with better-labelled data such that it can potentially outperform SoFiA.

Historic dress artifacts are a valuable source for human studies. In particular, they can provide important insights into the social aspects of their corresponding era. These insights are commonly drawn from garment pictures as well as the accompanying descriptions and are usually stored in a standardized and controlled vocabulary that accurately describes garments and costume items, called the Costume Core Vocabulary. Building an accurate Costume Core from garment descriptions can be challenging because the historic garment items are often donated, and the accompanying descriptions can be based on untrained individuals and use a language common to the period of the items. In this paper, we present an approach to use Natural Language Processing (NLP) to map the free-form text descriptions of the historic items to that of the controlled vocabulary provided by the Costume Core. Despite the limited dataset, we were able to train an NLP model based on the Universal Sentence Encoder to perform this mapping with more than 90% test accuracy for a subset of the Costume Core vocabulary. We describe our methodology, design choices, and development of our approach, and show the feasibility of predicting the Costume Core for unseen descriptions. With more garment descriptions still being curated to be used for training, we expect to have higher accuracy for better generalizability.

Attack Ensemble (AE), which combines multiple attacks together, provides a reliable way to evaluate adversarial robustness. In practice, AEs are often constructed and tuned by human experts, which however tends to be sub-optimal and time-consuming. In this work, we present AutoAE, a conceptually simple approach for automatically constructing AEs. In brief, AutoAE repeatedly adds the attack and its iteration steps to the ensemble that maximizes ensemble improvement per additional iteration consumed. We show theoretically that AutoAE yields AEs provably within a constant factor of the optimal for a given defense. We then use AutoAE to construct two AEs for $l_{\infty}$ and $l_2$ attacks, and apply them without any tuning or adaptation to 45 top adversarial defenses on the RobustBench leaderboard. In all except one cases we achieve equal or better (often the latter) robustness evaluation than existing AEs, and notably, in 29 cases we achieve better robustness evaluation than the best known one. Such performance of AutoAE shows itself as a reliable evaluation protocol for adversarial robustness, which further indicates the huge potential of automatic AE construction. Code is available at \url{https://github.com/LeegerPENG/AutoAE}.

Common Deep Metric Learning (DML) datasets specify only one notion of similarity, e.g., two images in the Cars196 dataset are deemed similar if they show the same car model. We argue that depending on the application, users of image retrieval systems have different and changing similarity notions that should be incorporated as easily as possible. Therefore, we present Language-Guided Zero-Shot Deep Metric Learning (LanZ-DML) as a new DML setting in which users control the properties that should be important for image representations without training data by only using natural language. To this end, we propose InDiReCT (Image representations using Dimensionality Reduction on CLIP embedded Texts), a model for LanZ-DML on images that exclusively uses a few text prompts for training. InDiReCT utilizes CLIP as a fixed feature extractor for images and texts and transfers the variation in text prompt embeddings to the image embedding space. Extensive experiments on five datasets and overall thirteen similarity notions show that, despite not seeing any images during training, InDiReCT performs better than strong baselines and approaches the performance of fully-supervised models. An analysis reveals that InDiReCT learns to focus on regions of the image that correlate with the desired similarity notion, which makes it a fast to train and easy to use method to create custom embedding spaces only using natural language.

Fairness in multiwinner elections is studied in varying contexts. For instance, diversity of candidates and representation of voters are both separately termed as being fair. A common denominator to ensure fairness across all such contexts is the use of constraints. However, across these contexts, the candidates selected to satisfy the given constraints may systematically lead to unfair outcomes for historically disadvantaged voter populations as the cost of fairness may be borne unequally. Hence, we develop a model to select candidates that satisfy the constraints fairly across voter populations. To do so, the model maps the constrained multiwinner election problem to a problem of fairly allocating indivisible goods. We propose three variants of the model, namely, global, localized, and inter-sectional. Next, we analyze the model's computational complexity, and we present an empirical analysis of the utility traded-off across various settings of our model across the three variants and discuss the impact of Simpson's paradox using synthetic datasets and a dataset of voting at the United Nations. Finally, we discuss the implications of our work for AI and machine learning, especially for studies that use constraints to guarantee fairness.

Large language models generate complex, open-ended outputs: instead of outputting a class label they write summaries, generate dialogue, or produce working code. In order to asses the reliability of these open-ended generation systems, we aim to identify qualitative categories of erroneous behavior, beyond identifying individual errors. To hypothesize and test for such qualitative errors, we draw inspiration from human cognitive biases -- systematic patterns of deviation from rational judgement. Specifically, we use cognitive biases as motivation to (i) generate hypotheses for problems that models may have, and (ii) develop experiments that elicit these problems. Using code generation as a case study, we find that OpenAI's Codex errs predictably based on how the input prompt is framed, adjusts outputs towards anchors, and is biased towards outputs that mimic frequent training examples. We then use our framework to elicit high-impact errors such as incorrectly deleting files. Our results indicate that experimental methodology from cognitive science can help characterize how machine learning systems behave.

Recent work has demonstrated that pre-trained language models (PLMs) are zero-shot learners. However, most existing zero-shot methods involve heavy human engineering or complicated self-training pipelines, hindering their application to new situations. In this work, we show that zero-shot text classification can be improved simply by clustering texts in the embedding spaces of PLMs. Specifically, we fit the unlabeled texts with a Bayesian Gaussian Mixture Model after initializing cluster positions and shapes using class names. Despite its simplicity, this approach achieves superior or comparable performance on both topic and sentiment classification datasets and outperforms prior works significantly on unbalanced datasets. We further explore the applicability of our clustering approach by evaluating it on 14 datasets with more diverse topics, text lengths, and numbers of classes. Our approach achieves an average of 20% absolute improvement over prompt-based zero-shot learning. Finally, we compare different PLM embedding spaces and find that texts are well-clustered by topics even if the PLM is not explicitly pre-trained to generate meaningful sentence embeddings. This work indicates that PLM embeddings can categorize texts without task-specific fine-tuning, thus providing a new way to analyze and utilize their knowledge and zero-shot learning ability.