Yevgen Matusevych

2 paper cards in Mova's library · 2019–2026

Yevgen Matusevych wrote 2 of the papers Mova reads, in 2019–2026, most of them on Dependency parsing, Part-of-speech tagging; often with Arianna Bisazza, Bastian Bunzeck, Francesca Padovani.

The profile is the library's match of the name; two people with one name are not always told apart.

Papers

CAIT: A Syntactic Parsing Toolkit for Child–Adult InTeractions (2026)
The authors train a biaffine dependency parser (SuPar, with RoBERTa-large) on the gold part of UD-English-CHILDES, about 48k manually corrected sentences, and add a POS tagger and an utterance-level construction tagger.
Are we there yet? Encoder-decoder neural networks as cognitive models of English past tense inflection (2019)
Kirov and Cotterell (2018) reported that an encoder-decoder network with attention fits human nonce-word past tenses better than an older rule model.