Related papers: Project Pipeline: Preservation, Persistence, and P…
Analysis pipelines commonly use high-level technologies that are popular when created, but are unlikely to be readable, executable, or sustainable in the long term. A set of criteria is introduced to address this problem: Completeness (no…
Retrieval-augmented generation over semi-structured sources such as HTML is constrained by a mismatch between document structure and the flat, sequence-based interfaces of today's embedding and generative models. Retrieval pipelines often…
The reproducibility of computational pipelines is an expectation in biomedical science, particularly in critical domains like human health. In this context, reporting next generation genome sequencing methods used in precision medicine…
Modern information retrieval systems often rely on multiple components executed in a pipeline. In a research setting, this can lead to substantial redundant computations (e.g., retrieving the same query multiple times for evaluating…
Academic research tends to focus on new models for document understanding creating a wide gap in the literature between model definition and running models at production scale. To close that gap, we present a microservice architecture that…
Persistent Identifiers (PID) are the foundation referencing digital assets in scientific publications, books, and digital repositories. In its realization, PIDs contain metadata and resolving targets in form of URLs that point to data sets…
We propose repair pipelining, a technique that speeds up the repair performance in general erasure-coded storage. By carefully scheduling the repair of failed data in small-size units across storage nodes in a pipelined manner, repair…
Robust machine learning relies on access to data that can be used with standardized frameworks in important tasks and the ability to develop models whose performance can be reasonably reproduced. In machine learning for healthcare, the…
Background: With the rapid growth of massively parallel sequencing technologies, still more laboratories are utilizing sequenced DNA fragments for genomic analyses. Interpretation of sequencing data is, however, strongly dependent on…
The accelerating pace of research on autoregressive generative models has produced thousands of papers, making manual literature surveys and reproduction studies increasingly impractical. We present a fully open-source, reproducible…
Bibliographic reference extraction and parsing are foundational for citation indexing, linking, and downstream scholarly knowledge-graph construction. However, most established evaluations focus on clean, English, end-of-document…
Recently there have been efforts to introduce new benchmark tasks for spoken language understanding (SLU), like semantic parsing. In this paper, we describe our proposed spoken semantic parsing system for the quality track (Track 1) in…
We propose an automated pipeline for performing literature reviews using semantic similarity. Unlike traditional systematic review systems or optimization based methods, this work emphasizes minimal overhead and high relevance by using…
In this study, we leverage a unique UNESCO collection of mid-20th century radio recordings to probe the robustness of modern off-the-shelf language identification (LID) and speaker recognition (SR) methods, especially with respect to the…
This paper presents a modular AI agentic skill pipeline for automating subject indexing with Library of Congress Subject Headings (LCSH). Subject indexing - the process of analyzing a work's aboutness, selecting controlled vocabulary terms,…
With the ever-increasing adoption of machine learning for data analytics, maintaining a machine learning pipeline is becoming more complex as both the datasets and trained models evolve with time. In a collaborative environment, the changes…
An increasing amount of research is being devoted to applying machine learning methods to electronic health record (EHR) data for various clinical purposes. This growing area of research has exposed the challenges of the accessibility of…
Spoken language understanding is typically based on pipeline architectures including speech recognition and natural language understanding steps. These components are optimized independently to allow usage of available data, but the overall…
Pulsar data analysis pipelines have historically been comprised of bespoke software systems, supporting the off-line analysis of data. However modern data acquisition systems are making off-line analyses impractical. They often output…
This paper describes a machine learning and data science pipeline for structured information extraction from documents, implemented as a suite of open-source tools and extensions to existing tools. It centers around a methodology for…