Speaker
Description
The surge in observational capabilities and the heightened focus on time-domain astronomy have led to a substantial increase in data volume, reshaping how astrophysicists interpret, process, and categorize information. Despite the utilization of machine-readable data formats in certain instances, a significant portion of information is conveyed through natural language reports. To address the challenge of analyzing vast amounts of textual data, our research endeavors to advance Natural Language Processing (NLP) methods. Our objective is to equip astronomers with automated tools capable of extracting and analyzing structured information in real-time, contributing to the enrichment of knowledge bases through the assimilation of observational reports. Our collaborative effort involves the integration of two independent NLP products: NIMBUS, an information extraction tool leveraging the OpenAI GPT-3.5+ model, and AstroNLPy, a tool utilizing Google's BERT models. We present their distinct capabilities in extracting specific information from astrophysical observation reports and highlight the synergies between the two systems within the Astro-COLIBRI platform, catering to both professional and amateur astronomers.
