Related papers: NeuRaLaTeX: A machine learning library written in …

We introduce the first application of the lean methodology to machine learning projects. Similar to lean startups and lean manufacturing, we argue that lean machine learning (LeanML) can drastically slash avoidable wastes in commercial…

With few exceptions, the field of Machine Learning (ML) research has largely ignored the browser as a computational engine. Beyond an educational resource for ML, the browser has vast potential to not only improve the state-of-the-art in ML…

We present a library to automatically embed signal processing and neural network predictions into the material robots are made of. Deep and shallow neural network models are first trained offline using state-of-the-art machine learning…

Relational databases (RDBs) are widely regarded as the gold standard for storing structured information. Consequently, predictive tasks leveraging this data format hold significant application promise. Recently, Relational Deep Learning…

This paper describes the Microsoft Translator submissions to the WMT19 news translation shared task for English-German. Our main focus is document-level neural machine translation with deep transformer models. We start with strong…

Accurately extracting structured content from PDFs is a critical first step for NLP over scientific papers. Recent work has improved extraction accuracy by incorporating elementary layout information, e.g., each token's 2D position on the…

Accurately converting pixel measurements into absolute real-world dimensions remains a fundamental challenge in computer vision and limits progress in key applications such as biomedicine, forensics, nutritional analysis, and e-commerce. We…

The field of scientific publishing that is served by LaTeX is increasingly dependent on the availability of metadata about publications. We discuss how to use LaTeX classes and BibTeX styles to curate metadata throughout the life cycle of a…

Effective text generation and chat interfaces for low-resource languages (LRLs) remain a challenge for state-of-the-art large language models (LLMs) to support. This is mainly due to the difficulty of curating high-quality instruction…

The conventional, widely used treatment of deep learning models as black boxes provides limited or no insights into the mechanisms that guide neural network decisions. Significant research effort has been dedicated to building interpretable…

HyperNetX (HNX) is an open source Python library for the analysis and visualization of complex network data modeled as hypergraphs. Initially released in 2019, HNX facilitates exploratory data analysis of complex networks using algebraic…

Hypernetworks, or hypernets for short, are neural networks that generate weights for another neural network, known as the target network. They have emerged as a powerful deep learning technique that allows for greater flexibility,…

We present ZipLex, a verified framework for invertible linear-time lexical analysis following the longest match (maximal munch) semantics. Unlike past verified lexers that focus only on satisfying the semantics of regular expressions and…

Scientific documents contain tables that list important information in a concise fashion. Structure and content extraction from tables embedded within PDF research documents is a very challenging task due to the existence of visual features…

Digital mathematical libraries (DMLs) such as arXiv, Numdam, and EuDML contain mainly documents from STEM fields, where mathematical formulae are often more important than text for understanding. Conventional information retrieval (IR)…

We present Regularized Linear Embedding (RLE), a novel method that projects a collection of linked documents (e.g. citation network) into a pretrained word embedding space. In addition to the textual content, we leverage a matrix of…

Visualisations drive all aspects of the Machine Learning (ML) Development Cycle but remain a vastly untapped resource by the research community. ML testing is a highly interactive and cognitive process which demands a human-in-the-loop…

Instead of relying on human-annotated training samples to build a classifier, weakly supervised scientific paper classification aims to classify papers only using category descriptions (e.g., category names, category-indicative keywords).…

Neural network architectures are most often conceptually designed and described in visual terms, but are implemented by writing error-prone code. PrototypeML is a machine learning development environment that bridges the dichotomy between…

Machine Learning is transitioning from an art and science into a technology available to every developer. In the near future, every application on every platform will incorporate trained models to encode data-based decisions that would be…