Existing emotion prediction benchmarks contain coarse emotion labels which do not consider the diversity of emotions that an image and text can elicit in humans due to various reasons. Learning diverse reactions to multimodal content is important as intelligent machines take a central role in generating and delivering content to society. To address this gap, we propose Socratis, a \underline{soc}ietal \underline{r}e\underline{a}c\underline{ti}on\underline{s} benchmark, where each image-caption (IC) pair is annotated with multiple emotions and the reasons for feeling them. Socratis contains 18K free-form reactions for 980 emotions on 2075 image-caption pairs from 5 widely-read news and image-caption (IC) datasets. We benchmark the capability of state-of-the-art multimodal large language models to generate the reasons for feeling an emotion given an IC pair. Based on a preliminary human study, we observe that humans prefer human-written reasons over 2 times more often than machine-generated ones. This shows our task is harder than standard generation tasks because it starkly contrasts recent findings where humans cannot tell apart machine vs human-written news articles, for instance. We further see that current captioning metrics based on large vision-language models also fail to correlate with human preferences. We hope that these findings and our benchmark will inspire further research on training emotionally aware models.
相關內容
The distribution-free chain ladder of Mack justified the use of the chain ladder predictor and enabled Mack to derive an estimator of conditional mean squared error of prediction for the chain ladder predictor. Classical insurance loss models, i.e. of compound Poisson type, are not consistent with Mack's distribution-free chain ladder. However, for a sequence of compound Poisson loss models indexed by exposure (e.g. number of contracts), we show that the chain ladder predictor and Mack's estimator of conditional mean squared error of prediction can be derived by considering large exposure asymptotics. Hence, quantifying chain ladder prediction uncertainty can be done with Mack's estimator without relying on the validity of the model assumptions of the distribution-free chain ladder.
Binwise Variance Scaling (BVS) has recently been proposed as a post hoc recalibration method for prediction uncertainties of machine learning regression problems that is able of more efficient corrections than uniform variance (or temperature) scaling. The original version of BVS uses uncertainty-based binning, which is aimed to improve calibration conditionally on uncertainty, i.e. consistency. I explore here several adaptations of BVS, in particular with alternative loss functions and a binning scheme based on an input-feature (X) in order to improve adaptivity, i.e. calibration conditional on X. The performances of BVS and its proposed variants are tested on a benchmark dataset for the prediction of atomization energies and compared to the results of isotonic regression.
Contributorship statements have been effective at recording granular author contributions in research articles and have been broadly used to understand how labor is divided across research teams. However, one major limitation in existing empirical studies is that two classification systems have been adopted, especially from its most important data source, journals published by the Public Library of Science (PLoS). This research aims to address this limitation by developing a mapping scheme between the two systems and using it to understand whether there are differences in the assignment of contribution by authors under the two systems. We use all research articles published in PLoS ONE between 2012 to 2020, divided into two five-year publication windows centered by the shift of the classification systems in 2016. Our results show that most tasks (except for writing- and resource-related tasks) are used similarly under the two systems. Moreover, notable differences between how researchers used the two systems are also examined and discussed. This research offers an important foundation for empirical research on division of labor in the future, by enabling a larger dataset that crosses both, and potentially other, classification systems.
In general insurance, claims are often lower-truncated and right-censored because insurance contracts may involve deductibles and maximal covers. Most classical statistical models are not (directly) suited to model lower-truncated and right-censored claims. A surprisingly flexible family of distributions that can cope with lower-truncated and right-censored claims is the class of MBBEFD distributions that originally has been introduced by Bernegger (1997) for reinsurance pricing, but which has not gained much attention outside the reinsurance literature. We derive properties of the class of MBBEFD distributions, and we extend it to a bigger family of distribution functions suitable for modeling lower-truncated and right-censored claims. Interestingly, in general insurance, we mainly rely on unimodal skewed densities, whereas the reinsurance literature typically proposes monotonically decreasing densities within the MBBEFD class.
Achieving accurate approximations to solutions of large linear systems is crucial, especially when those systems utilize real-world data. A consequence of using real-world data is that there will inevitably be missingness. Current approaches for dealing with missing data, such as deletion and imputation, can introduce bias. Recent studies proposed an adaptation of stochastic gradient descent (SGD) in specific missing-data models. In this work, we propose a new algorithm, $\ell$-tuple mSGD, for the setting in which data is missing in a block-wise, tuple pattern. We prove that our proposed method uses unbiased estimates of the gradient of the least squares objective in the presence of tuple missing data. We also draw connections between $\ell$-tuple mSGD and previously established SGD-type methods for missing data. Furthermore, we prove our algorithm converges when using updating step sizes and empirically demonstrate the convergence of $\ell$-tuple mSGD on synthetic data. Lastly, we evaluate $\ell$-tuple mSGD applied to real-world continuous glucose monitoring (CGM) device data.
We introduce time-ordered multibody interactions to describe complex systems manifesting temporal as well as multibody dependencies. First, we show how the dynamics of multivariate Markov chains can be decomposed in ensembles of time-ordered multibody interactions. Then, we present an algorithm to extract those interactions from data capturing the system-level dynamics of node states and a measure to characterize the complexity of interaction ensembles. Finally, we experimentally validate the robustness of our algorithm against statistical errors and its efficiency at inferring parsimonious interaction ensembles.
The identification and classification of political claims is an important step in the analysis of political newspaper reports; however, resources for this task are few and far between. This paper explores different strategies for the cross-lingual projection of political claims analysis. We conduct experiments on a German dataset, DebateNet2.0, covering the policy debate sparked by the 2015 refugee crisis. Our evaluation involves two tasks (claim identification and categorization), three languages (German, English, and French) and two methods (machine translation -- the best method in our experiments -- and multilingual embeddings).
Discrepancies in decision-making between Autonomous Driving Systems (ADS) and human drivers underscore the need for intuitive human gaze predictors to bridge this gap, thereby improving user trust and experience. Existing gaze datasets, despite their value, suffer from noise that hampers effective training. Furthermore, current gaze prediction models exhibit inconsistency across diverse scenarios and demand substantial computational resources, restricting their on-board deployment in autonomous vehicles. We propose a novel adaptive cleansing technique for purging noise from existing gaze datasets, coupled with a robust, lightweight convolutional self-attention gaze prediction model. Our approach not only significantly enhances model generalizability and performance by up to 12.13% but also ensures a remarkable reduction in model complexity by up to 98.2% compared to the state-of-the art, making in-vehicle deployment feasible to augment ADS decision visualization and performance.
Although measuring held-out accuracy has been the primary approach to evaluate generalization, it often overestimates the performance of NLP models, while alternative approaches for evaluating models either focus on individual tasks or on specific behaviors. Inspired by principles of behavioral testing in software engineering, we introduce CheckList, a task-agnostic methodology for testing NLP models. CheckList includes a matrix of general linguistic capabilities and test types that facilitate comprehensive test ideation, as well as a software tool to generate a large and diverse number of test cases quickly. We illustrate the utility of CheckList with tests for three tasks, identifying critical failures in both commercial and state-of-art models. In a user study, a team responsible for a commercial sentiment analysis model found new and actionable bugs in an extensively tested model. In another user study, NLP practitioners with CheckList created twice as many tests, and found almost three times as many bugs as users without it.
Compared with cheap addition operation, multiplication operation is of much higher computation complexity. The widely-used convolutions in deep neural networks are exactly cross-correlation to measure the similarity between input feature and convolution filters, which involves massive multiplications between float values. In this paper, we present adder networks (AdderNets) to trade these massive multiplications in deep neural networks, especially convolutional neural networks (CNNs), for much cheaper additions to reduce computation costs. In AdderNets, we take the $\ell_1$-norm distance between filters and input feature as the output response. The influence of this new similarity measure on the optimization of neural network have been thoroughly analyzed. To achieve a better performance, we develop a special back-propagation approach for AdderNets by investigating the full-precision gradient. We then propose an adaptive learning rate strategy to enhance the training procedure of AdderNets according to the magnitude of each neuron's gradient. As a result, the proposed AdderNets can achieve 74.9% Top-1 accuracy 91.7% Top-5 accuracy using ResNet-50 on the ImageNet dataset without any multiplication in convolution layer.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191