Multimodal sentiment analysis aims to recognize people's attitudes from multiple communication channels such as verbal content (i.e., text), voice, and facial expressions. It has become a vibrant and important research topic in natural language processing. Much research focuses on modeling the complex intra- and inter-modal interactions between different communication channels. However, current multimodal models with strong performance are often deep-learning-based techniques and work like black boxes. It is not clear how models utilize multimodal information for sentiment predictions. Despite recent advances in techniques for enhancing the explainability of machine learning models, they often target unimodal scenarios (e.g., images, sentences), and little research has been done on explaining multimodal models. In this paper, we present an interactive visual analytics system, M2Lens, to visualize and explain multimodal models for sentiment analysis. M2Lens provides explanations on intra- and inter-modal interactions at the global, subset, and local levels. Specifically, it summarizes the influence of three typical interaction types (i.e., dominance, complement, and conflict) on the model predictions. Moreover, M2Lens identifies frequent and influential multimodal features and supports the multi-faceted exploration of model behaviors from language, acoustic, and visual modalities. Through two case studies and expert interviews, we demonstrate our system can help users gain deep insights into the multimodal models for sentiment analysis.
Despite being a critical communication skill, grasping humor is challenging -- a successful use of humor requires a mixture of both engaging content build-up and an appropriate vocal delivery (e.g., pause). Prior studies on computational humor emphasize the textual and audio features immediately next to the punchline, yet overlooking longer-term context setup. Moreover, the theories are usually too abstract for understanding each concrete humor snippet. To fill in the gap, we develop DeHumor, a visual analytical system for analyzing humorous behaviors in public speaking. To intuitively reveal the building blocks of each concrete example, DeHumor decomposes each humorous video into multimodal features and provides inline annotations of them on the video script. In particular, to better capture the build-ups, we introduce content repetition as a complement to features introduced in theories of computational humor and visualize them in a context linking graph. To help users locate the punchlines that have the desired features to learn, we summarize the content (with keywords) and humor feature statistics on an augmented time matrix. With case studies on stand-up comedy shows and TED talks, we show that DeHumor is able to highlight various building blocks of humor examples. In addition, expert interviews with communication coaches and humor researchers demonstrate the effectiveness of DeHumor for multimodal humor analysis of speech content and vocal delivery.
This paper presents our systems for the three Subtasks of SemEval Task4: Reading Comprehension of Abstract Meaning (ReCAM). We explain the algorithms used to learn our models and the process of tuning the algorithms and selecting the best model. Inspired by the similarity of the ReCAM task and the language pre-training, we propose a simple yet effective technology, namely, negative augmentation with language model. Evaluation results demonstrate the effectiveness of our proposed approach. Our models achieve the 4th rank on both official test sets of Subtask 1 and Subtask 2 with an accuracy of 87.9% and an accuracy of 92.8%, respectively. We further conduct comprehensive model analysis and observe interesting error cases, which may promote future researches.
Self-training is a competitive approach in domain adaptive segmentation, which trains the network with the pseudo labels on the target domain. However inevitably, the pseudo labels are noisy and the target features are dispersed due to the discrepancy between source and target domains. In this paper, we rely on representative prototypes, the feature centroids of classes, to address the two issues for unsupervised domain adaptation. In particular, we take one step further and exploit the feature distances from prototypes that provide richer information than mere prototypes. Specifically, we use it to estimate the likelihood of pseudo labels to facilitate online correction in the course of training. Meanwhile, we align the prototypical assignments based on relative feature distances for two different views of the same target, producing a more compact target feature space. Moreover, we find that distilling the already learned knowledge to a self-supervised pretrained model further boosts the performance. Our method shows tremendous performance advantage over state-of-the-art methods. We will make the code publicly available.
Although convolutional neural networks (CNNs) are promoting the development of medical image semantic segmentation, the standard model still has some shortcomings. First, the feature mapping from the encoder and decoder sub-networks in the skip connection operation has a large semantic difference. Second, the remote feature dependence is not effectively modeled. Third, the global context information of different scales is ignored. In this paper, we try to eliminate semantic ambiguity in skip connection operations by adding attention gates (AGs), and use attention mechanisms to combine local features with their corresponding global dependencies, explicitly model the dependencies between channels and use multi-scale predictive fusion to utilize global information at different scales. Compared with other state-of-the-art segmentation networks, our model obtains better segmentation performance while introducing fewer parameters.
Graph Neural Networks (GNNs) aim to extend deep learning techniques to graph data and have achieved significant progress in graph analysis tasks (e.g., node classification) in recent years. However, similar to other deep neural networks like Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), GNNs behave like a black box with their details hidden from model developers and users. It is therefore difficult to diagnose possible errors of GNNs. Despite many visual analytics studies being done on CNNs and RNNs, little research has addressed the challenges for GNNs. This paper fills the research gap with an interactive visual analysis tool, GNNVis, to assist model developers and users in understanding and analyzing GNNs. Specifically, Parallel Sets View and Projection View enable users to quickly identify and validate error patterns in the set of wrong predictions; Graph View and Feature Matrix View offer a detailed analysis of individual nodes to assist users in forming hypotheses about the error patterns. Since GNNs jointly model the graph structure and the node features, we reveal the relative influences of the two types of information by comparing the predictions of three models: GNN, Multi-Layer Perceptron (MLP), and GNN Without Using Features (GNNWUF). Two case studies and interviews with domain experts demonstrate the effectiveness of GNNVis in facilitating the understanding of GNN models and their errors.
Modern neural machine translation (NMT) models employ a large number of parameters, which leads to serious over-parameterization and typically causes the underutilization of computational resources. In response to this problem, we empirically investigate whether the redundant parameters can be reused to achieve better performance. Experiments and analyses are systematically conducted on different datasets and NMT architectures. We show that: 1) the pruned parameters can be rejuvenated to improve the baseline model by up to +0.8 BLEU points; 2) the rejuvenated parameters are reallocated to enhance the ability of modeling low-level lexical information.
Student performance prediction is critical to online education. It can benefit many downstream tasks on online learning platforms, such as estimating dropout rates, facilitating strategic intervention, and enabling adaptive online learning. Interactive online question pools provide students with interesting interactive questions to practice their knowledge in online education. However, little research has been done on student performance prediction in interactive online question pools. Existing work on student performance prediction targets at online learning platforms with predefined course curriculum and accurate knowledge labels like MOOC platforms, but they are not able to fully model knowledge evolution of students in interactive online question pools. In this paper, we propose a novel approach using Graph Neural Networks (GNNs) to achieve better student performance prediction in interactive online question pools. Specifically, we model the relationship between students and questions using student interactions to construct the student-interaction-question network and further present a new GNN model, called R^2GCN, which intrinsically works for the heterogeneous networks, to achieve generalizable student performance prediction in interactive online question pools. We evaluate the effectiveness of our approach on a real-world dataset consisting of 104,113 mouse trajectories generated in the problem-solving process of over 4000 students on 1631 questions. The experiment results show that our approach can achieve a much higher accuracy of student performance prediction than both traditional machine learning approaches and GNN models.