The existing search tools for exploring the NASA Astrophysics Data System (ADS) can be quite rich and empowering (e.g., similar and trending operators), but researchers are not yet allowed to fully leverage semantic search. For example, a query for "results from the Planck mission" should be able to distinguish between all the various meanings of Planck (person, mission, constant, institutions and more) without further clarification from the user. At ADS, we are applying modern machine learning and natural language processing techniques to our dataset of recent astronomy publications to train astroBERT, a deeply contextual language model based on research at Google. Using astroBERT, we aim to enrich the ADS dataset and improve its discoverability, and in particular we are developing our own named entity recognition tool. We present here our preliminary results and lessons learned.

In this paper we provide an update concerning the operations of the NASA Astrophysics Data System (ADS), its services and user interface, and the content currently indexed in its database. As the primary information system used by researchers in Astronomy, the ADS aims to provide a comprehensive index of all scholarly resources appearing in the literature. With the current effort in our community to support data and software citations, we discuss what steps the ADS is taking to provide the needed infrastructure in collaboration with publishers and data providers. A new API provides access to the ADS search interface, metrics, and libraries allowing users to programmatically automate discovery and curation tasks. The new ADS interface supports a greater integration of content and services with a variety of partners, including ORCID claiming, indexing of SIMBAD objects, and article graphics from a variety of publishers. Finally, we highlight how librarians can facilitate the ingest of gray literature that they curate into our system. ⋆

Second Order Operators (SOOs) are database functions which form secondary queries based on attributes of the objects returned in an initial query; they can provide powerful methods to investigate complex, multipartite information graphs. The NASA Astrophysics Data System (ADS) has implemented four SOOs, reviews , useful , trending , and similar which use the citations, references, downloads, and abstract text. This tutorial describes these operators in detail, both alone and in conjunction with other functions. It is intended for scientists and others who wish to make fuller use of the ADS database. Basic knowledge of the ADS is assumed.

No abstract

No abstract