Yevgen Matusevych — accepted AI-conference papers

2025

Child-Directed Language Does Not Consistently Boost Syntax Learning in Language Models

Francesca Padovani, Jaap Jumelet, Yevgen Matusevych, Arianna Bisazza

EMNLP 2025

Seminal work by Huebner et al. (2021) showed that language models (LMs) trained on English Child-Directed Language (CDL) can outperform LMs trained on an equal amount of adult-directed text like Wikipedia. However, it remains unclear whether these results generalize across languages, architectures,

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2020

Multilingual Acoustic Word Embedding Models for Processing Zero-resource Languages

Herman Kamper, Yevgen Matusevych, Sharon Goldwater

ICASSP 2020accepted

Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. In settings where unlabelled speech is the only available resource, such embeddings can be used in "zero-resource" speech search, indexing and discovery systems. Here we propose to train a single super…

Cited by 0 Source ↗Scholar ↗