New Special Issue on Atoms of Representation in Natural Language Processing

A new special issue has been announced in the field of Applied Sciences titled Atoms of Representation in Natural Language Processing. This special issue aims to collect findings and insights on the question of how natural language in textual form can best be mapped into vector space. The focus is on the development and analysis of tokenization and untokenization methods, which is currently advancing at a slower rate compared to research in model architecture and optimization technologies. The issue encourages submissions on various themes including novel schemas for subword tokenization, benchmarks and analyses of tokenizer effectiveness, development of token-free representation schemata, and more. The full call for papers can be found at https://www.mdpi.com/journal/applsci/special_issues/2SHP0751R0.