Emotion recognition (ER) is an important task in Natural Language Processing (NLP), due to its high impact in real-world applications from health and well-being to author profiling, consumer analysis and security. Current approaches to ER, mainly classify emotions independently without considering that emotions can co-exist. Such approaches overlook potential ambiguities, in which multiple emotions overlap. We propose a new model "SpanEmo" casting multi-label emotion classification as span-prediction, which can aid ER models to learn associations between labels and words in a sentence. Furthermore, we introduce a loss function focused on modelling multiple co-existing emotions in the input sentence. Experiments performed on the SemEval2018 multi-label emotion data over three language sets (i.e., English, Arabic and Spanish) demonstrate our method's effectiveness. Finally, we present different analyses that illustrate the benefits of our method in terms of improving the model performance and learning meaningful associations between emotion classes and words in the sentence.
Histopathological characterization of colorectal polyps allows to tailor patients' management and follow up with the ultimate aim of avoiding or promptly detecting an invasive carcinoma. Colorectal polyps characterization relies on the histological analysis of tissue samples to determine the polyps malignancy and dysplasia grade. Deep neural networks achieve outstanding accuracy in medical patterns recognition, however they require large sets of annotated training images. We introduce UniToPatho, an annotated dataset of 9536 hematoxylin and eosin (H&E) stained patches extracted from 292 whole-slide images, meant for training deep neural networks for colorectal polyps classification and adenomas grading. We present our dataset and provide insights on how to tackle the problem of automatic colorectal polyps characterization.
Several methods have been explored for automating parts of Systematic Mapping (SM) and Systematic Review (SR) methodologies. Challenges typically evolve around the gaps in semantic understanding of text, as well as lack of domain and background knowledge necessary to bridge that gap. In this paper we investigate possible ways of automating parts of the SM/SR process, i.e. that of extracting keywords and key-phrases from scientific documents using unsupervised methods, which are then used as a basis to construct the corresponding Classification Scheme using semantic key-phrase clustering techniques. Specifically, we explore the effect of ensemble scores measure in key-phrase extraction, we explore semantic network based word embedding in embedding representation of phrase semantics and finally we also explore how clustering can be used to group related key-phrases. The evaluation is conducted on a dataset of publications pertaining the domain of "Explainable AI" which we constructed using standard publicly available digital libraries and sets of indexing terms (keywords). Results shows that: ensemble ranking score does improve the key-phrase extraction performance. Semantic-network based word embedding based on the ConceptNet Semantic Network has similar performance with contextualized word embedding, however the former are computationally more efficient. Finally Semantic key-phrase clustering at term-level can group similar terms together that can be suitable for classification scheme.
Loneliness does not only have emotional implications on a person but also on his/her well-being. The study of loneliness has been challenging and largely inconclusive in findings because of the several factors that might correlate to the phenomenon. We present one approach to predicting this event by discovering patterns of language associated with loneliness. Our results show insights and promising directions for mining text from instant messaging to predict loneliness.
Laws of large numbers guarantee that given a large enough sample from some population, the measure of any fixed sub-population is well-estimated by its frequency in the sample. We study laws of large numbers in sampling processes that can affect the environment they are acting upon and interact with it. Specifically, we consider the sequential sampling model proposed by Ben-Eliezer and Yogev (2020), and characterize the classes which admit a uniform law of large numbers in this model: these are exactly the classes that are \emph{online learnable}. Our characterization may be interpreted as an online analogue to the equivalence between learnability and uniform convergence in statistical (PAC) learning. The sample-complexity bounds we obtain are tight for many parameter regimes, and as an application, we determine the optimal regret bounds in online learning, stated in terms of \emph{Littlestone's dimension}, thus resolving the main open question from Ben-David, P\'al, and Shalev-Shwartz (2009), which was also posed by Rakhlin, Sridharan, and Tewari (2015).
In this paper, we present a transfer learning system to perform technical domain identification on multilingual text data. We have submitted two runs, one uses the transformer model BERT, and the other uses XLM-ROBERTa with the CNN model for text classification. These models allowed us to identify the domain of the given sentences for the ICON 2020 shared Task, TechDOfication: Technical Domain Identification. Our system ranked the best for the subtasks 1d, 1g for the given TechDOfication dataset.
Text classification is a fundamental problem in the field of natural language processing. Text classification mainly focuses on giving more importance to all the relevant features that help classify the textual data. Apart from these, the text can have redundant or highly correlated features. These features increase the complexity of the classification algorithm. Thus, many dimensionality reduction methods were proposed with the traditional machine learning classifiers. The use of dimensionality reduction methods with machine learning classifiers has achieved good results. In this paper, we propose a hybrid feature selection method for obtaining relevant features by combining various filter-based feature selection methods and fastText classifier. We then present three ways of implementing a feature selection and neural network pipeline. We observed a reduction in training time when feature selection methods are used along with neural networks. We also observed a slight increase in accuracy on some datasets.
Hybrid crowd-machine classifiers can achieve superior performance by combining the cost-effectiveness of automatic classification with the accuracy of human judgment. This paper shows how crowd and machines can support each other in tackling classification problems. Specifically, we propose an architecture that orchestrates active learning and crowd classification and combines them in a virtuous cycle. We show that when the pool of items to classify is finite we face learning vs. exploitation trade-off in hybrid classification, as we need to balance crowd tasks optimized for creating a training dataset with tasks optimized for classifying items in the pool. We define the problem, propose a set of heuristics and evaluate the approach on three real-world datasets with different characteristics in terms of machine and crowd classification performance, showing that our active hybrid approach significantly outperforms baselines.
The kidney biopsy based diagnosis of Lupus Nephritis (LN) is characterized by low inter-observer agreement, with misdiagnosis being associated with increased patient morbidity and mortality. Although various Computer Aided Diagnosis (CAD) systems have been developed for other nephrohistopathological applications, little has been done to accurately classify kidneys based on their kidney level Lupus Glomerulonephritis (LGN) scores. The successful implementation of CAD systems has also been hindered by the diagnosing physician's perceived classifier strengths and weaknesses, which has been shown to have a negative effect on patient outcomes. We propose an Uncertainty-Guided Bayesian Classification (UGBC) scheme that is designed to accurately classify control, class I/II, and class III/IV LGN (3 class) at both the glomerular-level classification task (26,634 segmented glomerulus images) and the kidney-level classification task (87 MRL/lpr mouse kidney sections). Data annotation was performed using a high throughput, bulk labeling scheme that is designed to take advantage of Deep Neural Network's (or DNNs) resistance to label noise. Our augmented UGBC scheme achieved a 94.5% weighted glomerular-level accuracy while achieving a weighted kidney-level accuracy of 96.6%, improving upon the standard Convolutional Neural Network (CNN) architecture by 11.8% and 3.5% respectively.
Mel-filterbanks are fixed, engineered audio features which emulate human perception and have been used through the history of audio understanding up to today. However, their undeniable qualities are counterbalanced by the fundamental limitations of handmade representations. In this work we show that we can train a single learnable frontend that outperforms mel-filterbanks on a wide range of audio signals, including speech, music, audio events and animal sounds, providing a general-purpose learned frontend for audio classification. To do so, we introduce a new principled, lightweight, fully learnable architecture that can be used as a drop-in replacement of mel-filterbanks. Our system learns all operations of audio features extraction, from filtering to pooling, compression and normalization, and can be integrated into any neural network at a negligible parameter cost. We perform multi-task training on eight diverse audio classification tasks, and show consistent improvements of our model over mel-filterbanks and previous learnable alternatives. Moreover, our system outperforms the current state-of-the-art learnable frontend on Audioset, with orders of magnitude fewer parameters.
An Orthogonal Least Squares (OLS) based feature selection method is proposed for both binomial and multinomial classification. The novel Squared Orthogonal Correlation Coefficient (SOCC) is defined based on Error Reduction Ratio (ERR) in OLS and used as the feature ranking criterion. The equivalence between the canonical correlation coefficient, Fisher's criterion, and the sum of the SOCCs is revealed, which unveils the statistical implication of ERR in OLS for the first time. It is also shown that the OLS based feature selection method has speed advantages when applied for greedy search. The proposed method is comprehensively compared with the mutual information based feature selection methods and the embedded methods using both synthetic and real world datasets. The results show that the proposed method is always in the top 5 among the 12 candidate methods. Besides, the proposed method can be directly applied to continuous features without discretisation, which is another significant advantage over mutual information based methods.
Fine-grained visual classification aims to recognize images belonging to multiple sub-categories within a same category. It is a challenging task due to the inherently subtle variations among highly-confused categories. Most existing methods only take an individual image as input, which may limit the ability of models to recognize contrastive clues from different images. In this paper, we propose an effective method called progressive co-attention network (PCA-Net) to tackle this problem. Specifically, we calculate the channel-wise similarity by encouraging interaction between the feature channels within same-category image pairs to capture the common discriminative features. Considering that complementary information is also crucial for recognition, we erase the prominent areas enhanced by the channel interaction to force the network to focus on other discriminative regions. The proposed model has achieved competitive results on three fine-grained visual classification benchmark datasets: CUB-200-2011, Stanford Cars, and FGVC Aircraft.
Lung auscultation is the most effective and indispensable method for diagnosing various respiratory disorders by using the sounds from the airways during inspirium and exhalation using a stethoscope. In this study, the statistical features are calculated from intrinsic mode functions that are extracted by applying the HilbertHuang Transform to the lung sounds from 12 different auscultation regions on the chest and back. The classification of the lung sounds from asthma and healthy subjects is performed using Deep Belief Networks (DBN). The DBN classifier model with two hidden layers has been tested using 5-fold cross validation method. The proposed DBN separated lung sounds from asthmatic and healthy subjects with high classification performance rates of 84.61%, 85.83%, and 77.11% for overall accuracy, sensitivity, and selectivity, respectively using frequencytime analysis.
SAR (VV and VH polarization) and optical data are widely used in image fusion to use the complimentary information of each other and to obtain the better-quality image (in terms of spatial and spectral features) for the improved classification results. This paper uses anisotropic diffusion with PCA for the fusion of SAR and optical data and patch-based SVM Classification with LBP (LBP-PSVM). Fusion results with VV polarization performed better than VH polarization using considered fusion method. For classification, the performance of LBP-PSVM using S1 (VV) with S2, S1 (VH) with S2 is compared with SVM classifier (without patch) and PSVM classifier (with patch), respectively. Classification results suggests that the LBP-PSVM classifier is more effective in comparison to SVM and PSVM classifiers for considered data.
Linear discriminant analysis (LDA) is a widely used algorithm in machine learning to extract a low-dimensional representation of high-dimensional data, it features to find the orthogonal discriminant projection subspace by using the Fisher discriminant criterion. However, the traditional Euclidean-based methods for solving LDA are easily convergent to spurious local minima and hardly obtain an optimal solution. To address such a problem, in this paper, we propose a novel algorithm namely Riemannian-based discriminant analysis (RDA) for subspace learning. In order to obtain an explicit solution, we transform the traditional Euclidean-based methods to the Riemannian manifold space and use the trust-region method to learn the discriminant projection subspace. We compare the proposed algorithm to existing variants of LDA, as well as the unsupervised tensor decomposition methods on image classification tasks. The numerical results suggest that RDA achieves state-of-the-art performance in classification accuracy.
We investigate the self-attention mechanism of BERT in a fine-tuning scenario for the classification of scientific articles over a taxonomy of research disciplines. We observe how self-attention focuses on words that are highly related to the domain of the article. Particularly, a small subset of vocabulary words tends to receive most of the attention. We compare and evaluate the subset of the most attended words with feature selection methods normally used for text classification in order to characterize self-attention as a possible feature selection approach. Using ConceptNet as ground truth, we also find that attended words are more related to the research fields of the articles. However, conventional feature selection methods are still a better option to learn classifiers from scratch. This result suggests that, while self-attention identifies domain-relevant terms, the discriminatory information in BERT is encoded in the contextualized outputs and the classification layer. It also raises the question whether injecting feature selection methods in the self-attention mechanism could further optimize single sequence classification using transformers.
Intent classification and slot filling are two critical tasks for natural language understanding. Traditionally the two tasks have been deemed to proceed independently. However, more recently, joint models for intent classification and slot filling have achieved state-of-the-art performance, and have proved that there exists a strong relationship between the two tasks. This article is a compilation of past work in natural language understanding, especially joint intent classification and slot filling. We observe three milestones in this research so far: Intent detection to identify the speaker's intention, slot filling to label each word token in the speech/text, and finally, joint intent classification and slot filling tasks. In this article, we describe trends, approaches, issues, data sets, evaluation metrics in intent classification and slot filling. We also discuss representative performance values, describe shared tasks, and provide pointers to future work, as given in prior works. To interpret the state-of-the-art trends, we provide multiple tables that describe and summarise past research along different dimensions, including the types of features, base approaches, and dataset domain used.
Federated Learning (FL) is a paradigm that aims to support loosely connected clients in learning a global model collaboratively with the help of a centralized server. The most popular FL algorithm is Federated Averaging (FedAvg), which is based on taking weighted average of the client models, with the weights determined largely based on dataset sizes at the clients. In this paper, we propose a new approach, termed Federated Node Selection (FedNS), for the server's global model aggregation in the FL setting. FedNS filters and re-weights the clients' models at the node/kernel level, hence leading to a potentially better global model by fusing the best components of the clients. Using collaborative image classification as an example, we show with experiments from multiple datasets and networks that FedNS can consistently achieve improved performance over FedAvg.
Contrastive learning has nearly closed the gap between supervised and self-supervised learning of image representations, and has also been explored for videos. However, prior work on contrastive learning for video data has not explored the effect of explicitly encouraging the features to be distinct across the temporal dimension. We develop a new temporal contrastive learning framework consisting of two novel losses to improve upon existing contrastive self-supervised video representation learning methods. The local-local temporal contrastive loss adds the task of discriminating between non-overlapping clips from the same video, whereas the global-local temporal contrastive aims to discriminate between timesteps of the feature map of an input clip in order to increase the temporal diversity of the learned features. Our proposed temporal contrastive learning framework achieves significant improvement over the state-of-the-art results in various downstream video understanding tasks such as action recognition, limited-label action classification, and nearest-neighbor video retrieval on multiple video datasets and backbones. We also demonstrate significant improvement in fine-grained action classification for visually similar classes. With the commonly used 3D ResNet-18 architecture with UCF101 pretraining, we achieve 82.4\% (+5.1\% increase over the previous best) top-1 accuracy on UCF101 and 52.9\% (+5.4\% increase) on HMDB51 action classification, and 56.2\% (+11.7\% increase) Top-1 Recall on UCF101 nearest neighbor video retrieval. Code released at github.com/DAVEISHAN/TCLR.
The classification of glomerular lesions is a routine and essential task in renal pathology. Recently, machine learning approaches, especially deep learning algorithms, have been used to perform computer-aided lesion characterization of glomeruli. However, one major challenge of developing such methods is the naturally imbalanced distribution of different lesions. In this paper, we propose CircleMix, a novel data augmentation technique, to improve the accuracy of classifying globally sclerotic glomeruli with a hierarchical learning strategy. Different from the recently proposed CutMix method, the CircleMix augmentation is optimized for the ball-shaped biomedical objects, such as glomeruli. 6,861 glomeruli with five classes (normal, periglomerular fibrosis, obsolescent glomerulosclerosis, solidified glomerulosclerosis, and disappearing glomerulosclerosis) were employed to develop and evaluate the proposed methods. From five-fold cross-validation, the proposed CircleMix augmentation achieved superior performance (Balanced Accuracy=73.0%) compared with the EfficientNet-B0 baseline (Balanced Accuracy=69.4%)