activity
20202022
most citedSyntax Representation in Word Embeddings and Neural Networks -- A Survey

1 citations · 1 across the 3 of their papers we have counts for

collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2022

A Balanced Data Approach for Evaluating Cross-Lingual Transfer: Mapping the Linguistic Blood Bank

Dan Malkin, Tomasz Limisiewicz, Gabriel Stanovsky

We show that the choice of pretraining languages affects downstream cross-lingual transfer for BERT-based models. We inspect zero-shot performance in balanced data conditions to mi…

cs.CL2021

Examining Cross-lingual Contextual Embeddings with Orthogonal Structural Probes

Tomasz Limisiewicz, David Mareček

State-of-the-art contextual embeddings are obtained from large language models available only for a few languages. For others, we need to learn representations using a multilingual…

cs.CL2020

Introducing Orthogonal Constraint in Structural Probes

Tomasz Limisiewicz, David Mareček

With the recent success of pre-trained models in NLP, a significant focus was put on interpreting their representations. One of the most prominent approaches is structural probing…

cs.CL2020

Gender Coreference and Bias Evaluation at WMT 2020

Tom Kocmi, Tomasz Limisiewicz, Gabriel Stanovsky

Gender bias in machine translation can manifest when choosing gender inflections based on spurious gender correlations. For example, always translating doctors as men and nurses as…

cs.CL20201 cited

Syntax Representation in Word Embeddings and Neural Networks -- A Survey

Tomasz Limisiewicz, David Mareček

Neural networks trained on natural language processing tasks capture syntax even though it is not provided as a supervision signal. This indicates that syntactic analysis is essent…

cs.CL2020

Universal Dependencies according to BERT: both more specific and more general

Tomasz Limisiewicz, Rudolf Rosa, David Mareček

This work focuses on analyzing the form and extent of syntactic abstraction captured by BERT by extracting labeled dependency trees from self-attentions. Previous work showed that…