Related papers: Extracting Scientific Figures with Distantly Super…
The availability of metadata for scientific documents is pivotal in propelling scientific knowledge forward and for adhering to the FAIR principles (i.e. Findability, Accessibility, Interoperability, and Reusability) of research findings.…
Recognizing the layout of unstructured digital documents is an important step when parsing the documents into structured machine-readable format for downstream applications. Deep neural networks that are developed for computer vision have…
Deep neural networks (DNNs) excel on fixed datasets but struggle with incremental and shifting data in real-world scenarios. Continual learning addresses this challenge by allowing models to learn from new data while retaining previously…
Scientific literature is one of the most significant resources for sharing knowledge. Researchers turn to scientific literature as a first step in designing an experiment. Given the extensive and growing volume of literature, the common…
Automated semantic segmentation of cell nuclei in microscopic images is crucial for disease diagnosis and tissue microenvironment analysis. Nonetheless, this task presents challenges due to the complexity and heterogeneity of cells. While…
Segmenting text into semantically coherent segments is an important task with applications in information retrieval and text summarization. Developing accurate topical segmentation requires the availability of training data with ground…
Large language models record impressive performance on many natural language processing tasks. However, their knowledge capacity is limited to the pretraining corpus. Retrieval augmentation offers an effective solution by retrieving context…
Labeling objects at a subordinate level typically requires expert knowledge, which is not always available when using random annotators. As such, learning directly from web images for fine-grained recognition has attracted broad attention.…
Previous work for text summarization in scientific domain mainly focused on the content of the input document, but seldom considering its citation network. However, scientific papers are full of uncommon domain-specific terms, making it…
Dataset distillation is a method for reducing dataset sizes by learning a small number of synthetic samples containing all the information of a large dataset. This has several benefits like speeding up model training, reducing energy…
Scientific contributions rarely develop in isolation, but instead build upon prior discoveries. We formulate the task of automated technological roadmapping as extracting scientific contributions from scholarly articles and linking them to…
Data $\textit{quality}$ is a crucial factor in the performance of machine learning models, a principle that dataset distillation methods exploit by compressing training datasets into much smaller counterparts that maintain similar…
In many machine learning applications, labeled data is scarce and obtaining more labels is expensive. We introduce a new approach to supervising neural networks by specifying constraints that should hold over the output space, rather than…
Document-level models for information extraction tasks like slot-filling are flexible: they can be applied to settings where information is not necessarily localized in a single sentence. For example, key features of a diagnosis in a…
Extracting information from academic PDF documents is crucial for numerous indexing, retrieval, and analysis use cases. Choosing the best tool to extract specific content elements is difficult because many, technically diverse tools are…
Scientific information extraction (SciIE) is critical for converting unstructured knowledge from scholarly articles into structured data (entities and relations). Several datasets have been proposed for training and validating SciIE models.…
Understanding key insights from full-text scholarly articles is essential as it enables us to determine interesting trends, give insight into the research and development, and build knowledge graphs. However, some of the interesting key…
Deep Convolutional Neural Networks (DCNNs) have recently been applied successfully to a variety of vision and multimedia tasks, thus driving development of novel solutions in several application domains. Document analysis is a particularly…
The text of clinical notes can be a valuable source of patient information and clinical assessments. Historically, the primary approach for exploiting clinical notes has been information extraction: linking spans of text to concepts in a…
Figures are essential channels for densely communicating complex ideas in scientific papers. Previous work in automatically generating figure captions has been largely unsuccessful and has defaulted to using single-layer LSTMs, which no…