Use of LLMs to Improve Affiliation Disambiguation in Alexandria3k

The growth of academic publications, heterogeneity of datasets and the absence of a globally accepted organization identifier introduce the challenge of affiliation disambiguation in bibliographic databases. In this paper, we create a baseline using the currently implemented algorithm for author affiliation linkage in Alexandria3k by comparing...

Author Name Disambiguation using Large Language Models: Contributions to a system for open reproducible publication research

Author name disambiguation, otherwise described as (publication) record linking, is a problem that has had considerable research dedicated to its solv- ing. Author attributions, calculating research met- rics and conducting literature reviews are amongst processes that experience increased difficulty due to ambiguous author names. In this study,...

Verifying the Semantics of Disambiguation Rules: Using Parse Tree Repairing for Showing Safety and Completeness of Associativity and Priority Rules

Context-free grammars (CFGs) provide a well-known formalism for the specification of programming languages. They describe the structure of a program in terms of parse trees. One major issue of CFGs is ambiguity, where one sentence can sometimes have multiple different parse trees. Some formalisms like SDF3 or YACC allow annotating a grammar with...