Large language models (LLMs) trained on general domain corpora showed remarkable results on natural language processing (NLP) tasks. However, previous research demonstrated LLMs trained using domain-focused corpora perform better on specialized tasks. Inspired by this insight, we developed INDUS, a comprehensive suite of LLMs tailored for the closely-related domains of Earth science, biology, physics, heliophysics, planetary sciences and astrophysics, and trained using curated scientific corpora drawn from diverse data sources. The suite of models include: (1) an encoder model trained using domain-specific vocabulary and corpora to address NLP tasks, (2) a contrastive-learning based text embedding model trained using a diverse set of datasets to address information retrieval tasks and (3) smaller versions of these models created using knowledge distillation for applications which have latency or resource constraints. We also created three new scientific benchmark datasets, Climate-Change NER (entity-recognition), NASA-QA (extractive QA) and NASA-IR (IR) to accelerate research in these multi-disciplinary fields. We show that our models outperform both general-purpose (RoBERTa) and domain- specific (SciBERT) encoders on these new tasks as well as existing tasks in the domains of interest. Furthermore, we demonstrate the use of these models in two industrial settings- as a retrieval model for large-scale vector search applications and in automatic content tagging systems.

Le manque de ressources annotées constitue un défi majeur pour le traitement automatique de la langue en astrophysique. Afin de combler cette lacune, nous présentons astroECR, une extension du corpus TDAC (Time-Domain Astrophysics Corpus). Notre corpus, constitué de 300 rapports d’observation en anglais, étend le schéma d’annotation initial de TDAC en introduisant cinq classes d’entités nommées supplémentaires spécifiques à l’astrophysique. Nous avons enrichi les annotations en incluant les coréférences, les relations sémantiques entre les objets célestes et leurs propriétés physiques, ainsi qu’en normalisant les noms d’objets célestes via des bases de données astronomiques. L’utilité de notre corpus est démontrée en fournissant des scores de référence à travers quatre tâches~: la reconnaissance d’entités nommées, la résolution de coréférences, la détection de relations, et la normalisation des noms d’objets célestes. Nous mettons à disposition le corpus ainsi que son guide d’annotation, les codes sources, et les modèles associés.

Interest in Astrophysical Natural Language Processing (NLP) has increased recently, fueled by the development of specialized language models for information extraction. However, the scarcity of annotated resources for this domain is still a significant challenge. Most existing corpora are limited to Named Entity Recognition (NER) tasks, leaving a gap in resource diversity. To address this gap and facilitate a broader spectrum of NLP research in astrophysics, we introduce astroECR, an extension of our previously built Time-Domain Astrophysics Corpus (TDAC). Our contributions involve expanding it to cover named entities, coreferences, annotations related to astrophysical relationships, and normalizing celestial object names. We showcase practical utility through baseline models for four NLP tasks and provide the research community access to our corpus, code, and models.

In this article, we describe the overview of our shared task: Detecting Entities in the Astrophysics Literature (DEAL). The DEAL shared task was part of the Workshop on Information Extraction from Scientific Publications (WIESP) in AACL-IJCNLP 2022. Information extraction from scientific publications is critical in several downstream tasks such as identification of critical entities, article summarization, citation classification, etc. The motivation of this shared task was to develop a community-wide effort for entity extraction from astrophysics literature. Automated entity extraction would help to build knowledge bases, high-quality meta-data for indexing and search, and several other use-cases of interests. Thirty-three teams registered for DEAL, twelve of them participated in the system runs, and finally four teams submitted their system descriptions. We analyze their system and performance and finally discuss the findings of DEAL.