13 citations · 35 across the 23 of their papers we have counts for
7 papers · 1 filter
Revisiting the Optimality of Word Lengths
Tiago Pimentel, Clara Meister, Ethan Gotlieb Wilcox +2
Zipf (1935) posited that wordforms are optimized to minimize utterances' communicative costs. Under the assumption that cost is given by an utterance's length, he supported this cl…
Counterfactual Probing for the Influence of Affect and Specificity on Intergroup Bias
Venkata S Govindarajan, Kyle Mahowald, David I. Beaver +1
While existing work on studying bias in NLP focues on negative or pejorative language use, Govindarajan et al. (2023) offer a revised framing of bias in terms of intergroup social…
A Method for Studying Semantic Construal in Grammatical Constructions with Interpretable Contextual Embedding Spaces
Gabriella Chronis, Kyle Mahowald, Katrin Erk
We study semantic construal in grammatical constructions using large language models. First, we project contextual word embeddings into three interpretable semantic spaces, each de…
Analogy in Contact: Modeling Maltese Plural Inflection
Sara Court, Andrea D. Sims, Micha Elsner
Maltese is often described as having a hybrid morphological system resulting from extensive contact between Semitic and Romance language varieties. Such a designation reflects an e…
Elaborative Simplification as Implicit Questions Under Discussion
Yating Wu, William Sheffield, Kyle Mahowald +1
Automated text simplification, a technique useful for making text more accessible to people such as children and emergent bilinguals, is often thought of as a monolingual translati…
A Discerning Several Thousand Judgments: GPT-3 Rates the Article + Adjective + Numeral + Noun Construction
Kyle Mahowald
Knowledge of syntax includes knowledge of rare, idiosyncratic constructions. LLMs must overcome frequency biases in order to master such constructions. In this study, I prompt GPT-…
For Generated Text, Is NLI-Neutral Text the Best Text?
Michail Mersinias, Kyle Mahowald
We explore incorporating natural language inference (NLI) into the text generative pipeline by using a pre-trained NLI model to assess whether a generated sentence entails, contrad…