Papers by Vitalii Hirak

2 papers
Assessing the Impact of Typological Features on Multilingual Machine Translation in the Age of Large Language Models (2026.eacl-long)

Copied to clipboard

Challenge: Existing evidence on the intrinsic difficulty of multilingual modeling is limited to small monolingual models or bilingual models trained from scratch.
Approach: They propose to use typological properties to determine the difficulty of modeling a language . they analyze two large pre-trained multilingual translation models .
Outcome: The proposed models are based on two large pre-trained models of encoder-decoder and decoder-only machine translation.
Attention on Multiword Expressions: A Multilingual Study of BERT-based Models with Regard to Idiomaticity and Microsyntax (2025.findings-naacl)

Copied to clipboard

Challenge: Specifically, models fine-tuned on semantic tasks tend to distribute attention to idiomatic expressions more evenly across layers.
Approach: They analyze attention patterns of encoder-only models towards two distinct types of Multiword Expressions (MWEs) idioms present challenges in semantic non-compositionality, while MSUs demonstrate unconventional syntactic behavior that does not conform to standard grammatical categorizations.
Outcome: The proposed models show that fine-tuned models allocate attention to idiomatic expressions more evenly across layers.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations