GLADIS: A General and Large Acronym Disambiguation Benchmark

Lihu Chen (1, 2, 3) , Gaël Varoquaux (4, 5, 3) , Fabian M. Suchanek (1, 2)

1 INFRES - Département Informatique et Réseaux
2 DIG - Data, Intelligence and Graphs
3 SODA - Méthodes computationnelles et mathématiques pour comprendre la société et la santé à partir de données
4 PARIETAL - Modelling brain structure, function and variability based on high-field MRI data
5 LNAO - Laboratoire de Neuroimagerie Assistée par Ordinateur

Acronym Disambiguation (AD) is crucial for natural language understanding on various sources, including biomedical reports, scientific papers, and search engine queries. However, existing acronym disambiguation benchmarks and tools are limited to specific domains, and the size of prior benchmarks is rather small. To accelerate the research on acronym disambiguation, we construct a new benchmark named GLADIS with three components: (1) a much larger acronym dictionary with 1.5M acronyms and 6.4M long forms; (2) a pre-training corpus with 160 million sentences; (3) three datasets that cover the general, scientific, and biomedical domains. We then pre-train a language model, AcroBERT, on our constructed corpus for general acronym disambiguation, and show the challenges and values of our new benchmark.

Keywords: Acronym Disambiguation; Entity Linking; Benchmark

Domains: Computer Science [cs]; Computation and Language [cs.CL]

Lihu Chen, Gaël Varoquaux, Fabian M. Suchanek. GLADIS: A General and Large Acronym Disambiguation Benchmark. EACL 2023 - The 17th Conference of the European Chapter of the Association for Computational Linguistics, May 2023, Dubrovnik, Croatia. ⟨hal-04039173⟩