Commonsense reasoning, aiming at endowing machines with a human-like ability to make situational presumptions, is extremely challenging to generalize. For someone who barely knows about "meditation," while is knowledgeable about "singing," he can still infer that "meditation makes people relaxed" from the existing knowledge that "singing makes people relaxed" by first conceptualizing "singing" as a "relaxing event" and then instantiating that event to "meditation." This process, known as conceptual induction and deduction, is fundamental to commonsense reasoning while lacking both labeled data and methodologies to enhance commonsense modeling. To fill such a research gap, we propose CAT (Contextualized ConceptuAlization and InsTantiation), a semi-supervised learning framework that integrates event conceptualization and instantiation to conceptualize commonsense knowledge bases at scale. Extensive experiments show that our framework achieves state-of-the-art performances on two conceptualization tasks, and the acquired abstract commonsense knowledge can significantly improve commonsense inference modeling. Our code, data, and fine-tuned models are publicly available at https://github.com/HKUST-KnowComp/CAT.

Private and public sector structures and norms refine how emerging technology is used in practice. In healthcare, despite a proliferation of AI adoption, the organizational governance surrounding its use and integration is often poorly understood. What the Health AI Partnership (HAIP) aims to do in this research is to better define the requirements for adequate organizational governance of AI systems in healthcare settings and support health system leaders to make more informed decisions around AI adoption. To work towards this understanding, we first identify how the standards for the AI adoption in healthcare may be designed to be used easily and efficiently. Then, we map out the precise decision points involved in the practical institutional adoption of AI technology within specific health systems. Practically, we achieve this through a multi-organizational collaboration with leaders from major health systems across the United States and key informants from related fields. Working with the consultancy IDEO [dot] org, we were able to conduct usability-testing sessions with healthcare and AI ethics professionals. Usability analysis revealed a prototype structured around mock key decision points that align with how organizational leaders approach technology adoption. Concurrently, we conducted semi-structured interviews with 89 professionals in healthcare and other relevant fields. Using a modified grounded theory approach, we were able to identify 8 key decision points and comprehensive procedures throughout the AI adoption lifecycle. This is one of the most detailed qualitative analyses to date of the current governance structures and processes involved in AI adoption by health systems in the United States. We hope these findings can inform future efforts to build capabilities to promote the safe, effective, and responsible adoption of emerging technologies in healthcare.

1. Citizen and community-science (CS) datasets have great potential for estimating interannual patterns of population change given the large volumes of data collected globally every year. Yet, the flexible protocols that enable many CS projects to collect large volumes of data typically lack the structure necessary to keep consistent sampling across years. This leads to interannual confounding, as changes to the observation process over time are confounded with changes in species population sizes. 2. Here we describe a novel modeling approach designed to estimate species population trends while controlling for the interannual confounding common in citizen science data. The approach is based on Double Machine Learning, a statistical framework that uses machine learning methods to estimate population change and the propensity scores used to adjust for confounding discovered in the data. Additionally, we develop a simulation method to identify and adjust for residual confounding missed by the propensity scores. Using this new method, we can produce spatially detailed trend estimates from citizen science data. 3. To illustrate the approach, we estimated species trends using data from the CS project eBird. We used a simulation study to assess the ability of the method to estimate spatially varying trends in the face of real-world confounding. Results showed that the trend estimates distinguished between spatially constant and spatially varying trends at a 27km resolution. There were low error rates on the estimated direction of population change (increasing/decreasing) and high correlations on the estimated magnitude. 4. The ability to estimate spatially explicit trends while accounting for confounding in citizen science data has the potential to fill important information gaps, helping to estimate population trends for species, regions, or seasons without rigorous monitoring data.

The Pearson-Matthews correlation coefficient (usually abbreviated MCC) is considered to be one of the most useful metrics for the performance of a binary classification or hypothesis testing method (for the sake of conciseness we will use the classification terminology throughout, but the concepts and methods discussed in the paper apply verbatim to hypothesis testing as well). For multinary classification tasks (with more than two classes) the existing extension of MCC, commonly called the $\text{R}_{\text{K}}$ metric, has also been successfully used in many applications. The present paper begins with an introductory discussion on certain aspects of MCC. Then we go on to discuss the topic of multinary classification that is the main focus of this paper and which, despite its practical and theoretical importance, appears to be less developed than the topic of binary classification. Our discussion of the $\text{R}_{\text{K}}$ is followed by the introduction of two other metrics for multinary classification derived from the multivariate Pearson correlation (MPC) coefficients. We show that both $\text{R}_{\text{K}}$ and the MPC metrics suffer from the problem of not decisively indicating poor classification results when they should, and introduce three new enhanced metrics that do not suffer from this problem. We also present an additional new metric for multinary classification which can be viewed as a direct extension of MCC.

Distance-based supervised method, the minimal learning machine, constructs a predictive model from data by learning a mapping between input and output distance matrices. In this paper, we propose methods and evaluate how this technique and its core component, the distance mapping, can be adapted to multi-label learning. The proposed approach is based on combining the distance mapping with an inverse distance weighting. Although the proposal is one of the simplest methods in the multi-label learning literature, it achieves state-of-the-art performance for small to moderate-sized multi-label learning problems. Besides its simplicity, the proposed method is fully deterministic and its hyper-parameter can be selected via ranking loss-based statistic which has a closed form, thus avoiding conventional cross-validation-based hyper-parameter tuning. In addition, due to its simple linear distance mapping-based construction, we demonstrate that the proposed method can assess predictions' uncertainty for multi-label classification, which is a valuable capability for data-centric machine learning pipelines.

Local news articles are a subset of news that impact users in a geographical area, such as a city, county, or state. Detecting local news (Step 1) and subsequently deciding its geographical location as well as radius of impact (Step 2) are two important steps towards accurate local news recommendation. Naive rule-based methods, such as detecting city names from the news title, tend to give erroneous results due to lack of understanding of the news content. Empowered by the latest development in natural language processing, we develop an integrated pipeline that enables automatic local news detection and content-based local news recommendations. In this paper, we focus on Step 1 of the pipeline, which highlights: (1) a weakly supervised framework incorporated with domain knowledge and auto data processing, and (2) scalability to multi-lingual settings. Compared with Stanford CoreNLP NER model, our pipeline has higher precision and recall evaluated on a real-world and human-labeled dataset. This pipeline has potential to more precise local news to users, helps local businesses get more exposure, and gives people more information about their neighborhood safety.

Machine learning models exhibit two seemingly contradictory phenomena: training data memorization, and various forms of forgetting. In memorization, models overfit specific training examples and become susceptible to privacy attacks. In forgetting, examples which appeared early in training are forgotten by the end. In this work, we connect these phenomena. We propose a technique to measure to what extent models "forget" the specifics of training examples, becoming less susceptible to privacy attacks on examples they have not seen recently. We show that, while non-convex models can memorize data forever in the worst-case, standard image, speech, and language models empirically do forget examples over time. We identify nondeterminism as a potential explanation, showing that deterministically trained models do not forget. Our results suggest that examples seen early when training with extremely large datasets - for instance those examples used to pre-train a model - may observe privacy benefits at the expense of examples seen later.

Recommender systems can strongly influence which information we see online, e.g., on social media, and thus impact our beliefs, decisions, and actions. At the same time, these systems can create substantial business value for different stakeholders. Given the growing potential impact of such AI-based systems on individuals, organizations, and society, questions of fairness have gained increased attention in recent years. However, research on fairness in recommender systems is still a developing area. In this survey, we first review the fundamental concepts and notions of fairness that were put forward in the area in the recent past. Afterward, through a review of more than 160 scholarly publications, we present an overview of how research in this field is currently operationalized, e.g., in terms of general research methodology, fairness measures, and algorithmic approaches. Overall, our analysis of recent works points to certain research gaps. In particular, we find that in many research works in computer science, very abstract problem operationalizations are prevalent and questions of the underlying normative claims and what represents a fair recommendation in the context of a given application are often not discussed in depth. These observations call for more interdisciplinary research to address fairness in recommendation in a more comprehensive and impactful manner.

Phone-level pronunciation scoring is a challenging task, with performance far from that of human annotators. Standard systems generate a score for each phone in a phrase using models trained for automatic speech recognition (ASR) with native data only. Better performance has been shown when using systems that are trained specifically for the task using non-native data. Yet, such systems face the challenge that datasets labelled for this task are scarce and usually small. In this paper, we present a transfer learning-based approach that leverages a model trained for ASR, adapting it for the task of pronunciation scoring. We analyze the effect of several design choices and compare the performance with a state-of-the-art goodness of pronunciation (GOP) system. Our final system is 20% better than the GOP system on EpaDB, a database for pronunciation scoring research, for a cost function that prioritizes low rates of unnecessary corrections.

A kriging-random forest hybrid model is developed for real-time ground property prediction ahead of the earth pressure balanced shield by integrating Kriging extrapolation and random forest, which can guide shield operating parameter selection thereby mitigate construction risks. The proposed KRF algorithm synergizes two types of information: prior information and real-time information. The previously predicted ground properties with EPB operating parameters are extrapolated via the Kriging algorithm to provide prior information for the prediction of currently being excavated ground properties. The real-time information refers to the real-time operating parameters of the EPB shield, which are input into random forest to provide a real-time prediction of ground properties. The integration of these two predictions is achieved by assigning weights to each prediction according to their uncertainties, ensuring the prediction of KRF with minimum uncertainty. The performance of the KRF algorithm is assessed via a case study of the Changsha Metro Line 4 project. It reveals that the proposed KRF algorithm can predict ground properties with an accuracy of 93%, overperforming the existing algorithms of LightGBM, AdaBoost-CART, and DNN by 29%, 8%, and 12%, respectively. Another dataset from Shenzhen Metro Line 13 project is utilized to further evaluate the model generalization performance, revealing that the model can transfer its learned knowledge from one region to another with an accuracy of 89%.