Kyle Mahowald

What do tokens know about their characters and how do they know it?

2022 · arXiv (Cornell University)

Pre-trained language models (PLMs) that use subword tokenization schemes can succeed at a variety of language tasks that require character-level information, despite lacking explicit access to the character composition of tokens. Here, studying a range …

A Method for Studying Semantic Construal in Grammatical Constructions with Interpretable Contextual Embedding Spaces

2023

We study semantic construal in grammatical constructions using large language models. First, we project contextual word embeddings into three interpretable semantic spaces, each defined by a different set of psycholinguistic feature norms. We validate these …

Large-scale evidence of dependency length minimization in 37 languages

2015 · Proceedings of the National Academy of Sciences

Explaining the variation between human languages and the constraints on that variation is a core goal of linguistics. In the last 20 y, it has been claimed that many striking universals of cross-linguistic variation follow …