Noun compounds constitute a challenging construction for NLP applications, given their variability in idiomaticity and interpretation. In this paper, we present an analysis of compound nouns identified in Irish text of varied domains by expert annotators, focusing on compositionality as a key feature, but also domain specificity, as well as familiarity and confidence of the annotator giving the ratings. Our findings and the discussion that ensued contributes towards a greater understanding of how these constructions appear in Irish language, and how they might be treated separately from English noun compounds.

In recent years, the development of smart edge computing systems to process information locally is on the rise. Many near-sensor machine learning (ML) approaches have been implemented to introduce accurate and energy efficient template matching operations in resource-constrained edge sensing systems, such as wearables. To introduce novel solutions that can be viable for extreme edge cases, hybrid solutions combining conventional and emerging technologies have started to be proposed. Deep Neural Networks (DNN) optimised for edge application alongside new approaches of computing (both device and architecture -wise) could be a strong candidate in implementing edge ML solutions that aim at competitive accuracy classification while using a fraction of the power of conventional ML solutions. In this work, we are proposing a hybrid software-hardware edge classifier aimed at the extreme edge near-sensor systems. The classifier consists of two parts: (i) an optimised digital tinyML network, working as a front-end feature extractor, and (ii) a back-end RRAM-CMOS analogue content addressable memory (ACAM), working as a final stage template matching system. The combined hybrid system exhibits a competitive trade-off in accuracy versus energy metric with $E_{front-end}$ = $96.23 nJ$ and $E_{back-end}$ = $1.45 nJ$ for each classification operation compared with 78.06$\mu$J for the original teacher model, representing a 792-fold reduction, making it a viable solution for extreme edge applications.

Physical activity energy expenditure (PAEE) can be measured from breath-by-breath respiratory data, which can serve as a reference. Alternatively, PAEE can be predicted from the body movements, which can be measured and estimated with accelerometers. The body center of mass (COM) acceleration reflects the movements of the whole body and thus serves as a good predictor for PAEE. However, the wrist has also become a popular location due to recent advancements in wrist-worn devices. Therefore, in this work, using the respiratory data measured by COSMED K5 as the reference, we evaluated and compared the performances of COM-based settings and wrist-based settings. The COM-based settings include two different accelerometer compositions, using only the pelvis accelerometer (pelvis-acc) and the pelvis accelerometer with two accelerometers from two thighs (3-acc). The wrist-based settings include using only the left wrist accelerometer (l-wrist-acc) and only the right wrist accelerometer (r-wrist-acc). We implemented two existing PAEE estimation methods on our collected dataset, where 9 participants performed activities of daily living while wearing 5 accelerometers (i.e., pelvis, two thighs, and two wrists). These two methods include a linear regression (LR) model and a CNN-LSTM model. Both models yielded the best results with the COM-based 3-acc setting (LR: $R^2$ = 0.41, CNN-LSTM: $R^2$ = 0.53). No significant difference was found between the 3-acc and pelvis-acc settings (p-value = 0.278). For both models, neither the l-wrist-acc nor the r-wrist-acc settings demonstrated predictive power on PAEE with $R^2$ values close to 0, significantly outperformed by the two COM-based settings (p-values $<$ 0.05). No significant difference was found between the two wrists (p-value = 0.329).

Partial-label learning (PLL) is a weakly supervised learning problem in which each example is associated with multiple candidate labels and only one is the true label. In recent years, many deep PLL algorithms have been developed to improve model performance. However, we find that some early developed algorithms are often underestimated and can outperform many later algorithms with complicated designs. In this paper, we delve into the empirical perspective of PLL and identify several critical but previously overlooked issues. First, model selection for PLL is non-trivial, but has never been systematically studied. Second, the experimental settings are highly inconsistent, making it difficult to evaluate the effectiveness of the algorithms. Third, there is a lack of real-world image datasets that can be compatible with modern network architectures. Based on these findings, we propose PLENCH, the first Partial-Label learning bENCHmark to systematically compare state-of-the-art deep PLL algorithms. We investigate the model selection problem for PLL for the first time, and propose novel model selection criteria with theoretical guarantees. We also create Partial-Label CIFAR-10 (PLCIFAR10), an image dataset of human-annotated partial labels collected from Amazon Mechanical Turk, to provide a testbed for evaluating the performance of PLL algorithms in more realistic scenarios. Researchers can quickly and conveniently perform a comprehensive and fair evaluation and verify the effectiveness of newly developed algorithms based on PLENCH. We hope that PLENCH will facilitate standardized, fair, and practical evaluation of PLL algorithms in the future.

Diverse schools can help address implicit biases and increase empathy, mutual respect, and reflective thought by fostering connections between students from different racial/ethnic, socioeconomic, and other backgrounds. Unfortunately, demographic segregation remains rampant in US public schools, despite over 70 years since the passing of federal legislation formally outlawing segregation by race. However, changing how students are assigned to schools can help foster more integrated learning environments. In this paper, we explore "school mergers" as one such under-explored, yet promising, student assignment policy change. School mergers involve merging the school attendance boundaries, or catchment areas, of schools and subsequently changing the grades each school offers. We develop an algorithm to simulate elementary school mergers across 200 large school districts serving 4.5 million elementary school students and find that pairing or tripling schools in this way could reduce racial/ethnic segregation by a median relative 20% -- and as much as nearly 60% in some districts -- while increasing driving times to schools by an average of a few minutes each way. Districts with many interfaces between racially/ethnically-disparate neighborhoods tend to be prime candidates for mergers. We also compare the expected results of school mergers to other typical integration policies, like redistricting, and find that different policies may be more or less suitable in different places. Finally, we make our results available through a public dashboard for policymakers and community members to explore further (https://mergers.schooldiversity.org). Together, our study offers new findings and tools to support integration policy-making across US public school districts.

We introduce model folding, a novel data-free model compression technique that merges structurally similar neurons across layers, significantly reducing the model size without the need for fine-tuning or access to training data. Unlike existing methods, model folding preserves data statistics during compression by leveraging k-means clustering, and using novel data-free techniques to prevent variance collapse or explosion. Our theoretical framework and experiments across standard benchmarks, including ResNet18 and LLaMA-7B, demonstrate that model folding achieves comparable performance to data-driven compression techniques and outperforms recently proposed data-free methods, especially at high sparsity levels. This approach is particularly effective for compressing large-scale models, making it suitable for deployment in resource-constrained environments.

Modern language models are trained on large, unstructured datasets consisting of trillions of tokens and obtained by crawling the web. The unstructured nature makes it difficult to reason about their contents and develop systematic approaches to data curation. In this paper, we unpack monolithic web corpora by developing taxonomies of their contents and organizing them into domains. We introduce WebOrganizer, a framework for organizing web pages in terms of both their topic and format. Using these two complementary notions of domains, we automatically annotate pre-training data by distilling annotations from a large language model into efficient classifiers. This allows us to study how data from different domains should be mixed to improve models on downstream tasks, and we show that we can combine insights about effective topics and formats to further boost performance. We demonstrate that our domain mixing also improves existing methods that select data based on quality. Furthermore, we study and compare how quality-based methods will implicitly change the domain mixture. Overall, our work demonstrates that constructing and mixing domains provides a valuable complement to quality-based data curation methods, opening new avenues for effective and insightful pre-training data curation.

English as a Second Language (ESL) learners often encounter unknown words that hinder their text comprehension. Automatically detecting these words as users read can enable computing systems to provide just-in-time definitions, synonyms, or contextual explanations, thereby helping users learn vocabulary in a natural and seamless manner. This paper presents EyeLingo, a transformer-based machine learning method that predicts the probability of unknown words based on text content and eye gaze trajectory in real time with high accuracy. A 20-participant user study revealed that our method can achieve an accuracy of 97.6%, and an F1-score of 71.1%. We implemented a real-time reading assistance prototype to show the effectiveness of EyeLingo. The user study shows improvement in willingness to use and usefulness compared to baseline methods.

Reasoning about fairness through correlation-based notions is rife with pitfalls. The 1973 University of California, Berkeley graduate school admissions case from Bickel et. al. (1975) is a classic example of one such pitfall, namely Simpson's paradox. The discrepancy in admission rates among males and female applicants, in the aggregate data over all departments, vanishes when admission rates per department are examined. We reason about the Berkeley graduate school admissions case through a causal lens. In the process, we introduce a statistical test for causal hypothesis testing based on Pearl's instrumental-variable inequalities (Pearl 1995). We compare different causal notions of fairness that are based on graphical, counterfactual and interventional queries on the causal model, and develop statistical tests for these notions that use only observational data. We study the logical relations between notions, and show that while notions may not be equivalent, their corresponding statistical tests coincide for the case at hand. We believe that a thorough case-based causal analysis helps develop a more principled understanding of both causal hypothesis testing and fairness.

In order to develop practical and efficient algorithms while circumventing overly pessimistic computational lower bounds, recent work has been interested in developing oracle-efficient algorithms in a variety of learning settings. Two such settings of particular interest are online and differentially private learning. While seemingly different, these two fields are fundamentally connected by the requirement that successful algorithms in each case satisfy stability guarantees; in particular, recent work has demonstrated that algorithms for online learning whose performance adapts to beneficial problem instances, attaining the so-called small-loss bounds, require a form of stability similar to that of differential privacy. In this work, we identify the crucial role that separation plays in allowing oracle-efficient algorithms to achieve this strong stability. Our notion, which we term $\rho$-separation, generalizes and unifies several previous approaches to enforcing this strong stability, including the existence of small-separator sets and the recent notion of $\gamma$-approximability. We present an oracle-efficient algorithm that is capable of achieving small-loss bounds with improved rates in greater generality than previous work, as well as a variant for differentially private learning that attains optimal rates, again under our separation condition. In so doing, we prove a new stability result for minimizers of a Gaussian process that strengthens and generalizes previous work.