Related papers: Abstractified Multi-instance Learning (AMIL) for B…
Categorical speech emotion recognition is typically performed as a sequence-to-label problem, i.e., to determine the discrete emotion label of the input utterance as a whole. One of the main challenges in practice is that most of the…
Knowledge-based question answering relies on the availability of facts, the majority of which cannot be found in structured sources (e.g. Wikipedia info-boxes, Wikidata). One of the major components of extracting facts from unstructured…
Instance-aware embeddings predicted by deep neural networks have revolutionized biomedical instance segmentation, but its resource requirements are substantial. Knowledge distillation offers a solution by transferring distilled knowledge…
In recent years, biomedical event extraction has been dominated by complicated pipeline and joint methods, which need to be simplified. In addition, existing work has not effectively utilized trigger word information explicitly. Hence, we…
Automated disease diagnosis using medical image analysis relies on deep learning, often requiring large labeled datasets for supervised model training. Diseases like Acute Myeloid Leukemia (AML) pose challenges due to scarce and costly…
Hispathological image segmentation algorithms play a critical role in computer aided diagnosis technology. The development of weakly supervised segmentation algorithm alleviates the problem of medical image annotation that it is…
Transfer learning from large-scale pre-trained models has become essential for many computer vision tasks. Recent studies have shown that datasets like ImageNet are weakly labeled since images with multiple object classes present are…
Multiple instance learning (MIL) is a variation of traditional supervised learning problems where data (referred to as bags) are composed of sub-elements (referred to as instances) and only bag labels are available. MIL has a variety of…
Multiple instance learning (MIL) problem is currently solved from either bag-classification or instance-classification perspective, both of which ignore important information contained in some instances and result in limited performance.…
Recent research efforts have explored the potential of leveraging natural language inference (NLI) techniques to enhance relation extraction (RE). In this vein, we introduce MetaEntailRE, a novel adaptation method that harnesses NLI…
Information extraction techniques, including named entity recognition (NER) and relation extraction (RE), are crucial in many domains to support making sense of vast amounts of unstructured text data by identifying and connecting relevant…
Multi-instance learning (MIL) is an effective paradigm for whole-slide pathological images (WSIs) classification to handle the gigapixel resolution and slide-level label. Prevailing MIL methods primarily focus on improving the feature…
Joint medical relation extraction refers to extracting triples, composed of entities and relations, from the medical text with a single model. One of the solutions is to convert this task into a sequential tagging task. However, in the…
Using different sources of information to support automated extracting of relations between biomedical concepts contributes to the development of our understanding of biological systems. The primary comprehensive source of these relations…
Active Learning methods create an optimized labeled training set from unlabeled data. We introduce a novel Online Active Deep Learning method for Medical Image Analysis. We extend our MedAL active learning framework to present new results…
Manual annotation of the labeled data for relation extraction is time-consuming and labor-intensive. Semi-supervised methods can offer helping hands for this problem and have aroused great research interests. Existing work focuses on…
When applying multi-instance learning (MIL) to make predictions for bags of instances, the prediction accuracy of an instance often depends on not only the instance itself but also its context in the corresponding bag. From the viewpoint of…
This paper addresses the challenges posed by the unstructured nature and high-dimensional semantic complexity of electronic health record texts. A deep learning method based on attention mechanisms is proposed to achieve unified modeling…
Document-level relation extraction faces two overlooked challenges: long-tail problem and multi-label problem. Previous work focuses mainly on obtaining better contextual representations for entity pairs, hardly address the above…
In relation extraction with distant supervision, noisy labels make it difficult to train quality models. Previous neural models addressed this problem using an attention mechanism that attends to sentences that are likely to express the…