Search Results for author: Cass Jacobs

Found 4 papers, 0 papers with code

The human unlikeness of neural language models in next-word prediction

no code implementations WS 2020 Cass Jacobs, ra L., Arya D. McCarthy

The training objective of unidirectional language models (LMs) is similar to a psycholinguistic benchmark known as the cloze task, which measures next-word predictability.

Encoder-decoder models for latent phonological representations of words

no code implementations WS 2019 Cass Jacobs, ra L., Fred Mailhot

We use sequence-to-sequence networks trained on sequential phonetic encoding tasks to construct compositional phonological representations of words.

Cannot find the paper you are looking for? You can Submit a new open access paper.