833 citations · 4.3k across the 84 of their papers we have counts for
21 papers · 1 filter
A suite of allotaxonometric tools for the comparison of complex systems using rank-turbulence divergence
Jonathan St-Onge, Ashley M. A. Fehr, Carter Ward +6
Describing and comparing complex systems requires principled, theoretically grounded tools. Built around the phenomenon of type turbulence, allotaxonographs provide map-and-list vi…
Tokens, the oft-overlooked appetizer: Large language models, the distributional hypothesis, and meaning
Julia Witte Zimmerman, Denis Hudon, Kathryn Cramer +9
Tokenization is a necessary component within the current architecture of many language mod-els, including the transformer-based large language models (LLMs) of Generative AI, yet i…
A blind spot for large language models: Supradiegetic linguistic information
Julia Witte Zimmerman, Denis Hudon, Kathryn Cramer +5
Large Language Models (LLMs) like ChatGPT reflect profound changes in the field of Artificial Intelligence, achieving a linguistic fluency that is impressively, even shockingly, hu…
Curating corpora with classifiers: A case study of clean energy sentiment online
Michael V. Arnold, Peter Sheridan Dodds, Christopher M. Danforth
Well curated, large-scale corpora of social media posts containing broad public opinion offer an alternative data source to complement traditional surveys. While surveys are effect…
A decomposition of book structure through ousiometric fluctuations in cumulative word-time
Mikaela Irene Fudolig, Thayer Alshaabi, Kathryn Cramer +2
While quantitative methods have been used to examine changes in word usage in books, studies have focused on overall trends, such as the shapes of narratives, which are independent…
Augmenting semantic lexicons using word embeddings and transfer learning
Thayer Alshaabi, Colin M. Van Oort, Mikaela Irene Fudolig +3
Sentiment-aware intelligent systems are essential to a wide array of applications. These systems are driven by language models which broadly fall into two paradigms: Lexicon-based…