UnScientify: Detecting Scientific Uncertainty in Scholarly Full Text

TL;DR

UnScientify is an interactive system that detects scientific uncertainty in scholarly texts using a weakly supervised approach, aiding information retrieval and text analysis with interpretable results.

Contribution

It introduces a novel weakly supervised method for sentence-level uncertainty detection in scientific texts with an interpretable output.

Findings

Automates uncertainty annotation in scientific texts

Handles various types of scientific uncertainty

Provides interpretable uncertainty detection results

Abstract

This demo paper presents UnScientify, an interactive system designed to detect scientific uncertainty in scholarly full text. The system utilizes a weakly supervised technique that employs a fine-grained annotation scheme to identify verbally formulated uncertainty at the sentence level in scientific texts. The pipeline for the system includes a combination of pattern matching, complex sentence checking, and authorial reference checking. Our approach automates labeling and annotation tasks for scientific uncertainty identification, taking into account different types of scientific uncertainty, that can serve various applications such as information retrieval, text mining, and scholarly document processing. Additionally, UnScientify provides interpretable results, aiding in the comprehension of identified instances of scientific uncertainty in text.