6 citations · 15 across the 8 of their papers we have counts for
8 papers
Exploring the Impact of Training Data Distribution and Subword Tokenization on Gender Bias in Machine Translation
Bar Iluz, Tomasz Limisiewicz, Gabriel Stanovsky +1
We study the effect of tokenization on gender bias in machine translation, an aspect that has been largely overlooked in previous works. Specifically, we focus on the interactions…
Tokenization Impacts Multilingual Language Modeling: Assessing Vocabulary Allocation and Overlap Across Languages
Tomasz Limisiewicz, Jiří Balhar, David Mareček
Multilingual language models have recently gained attention as a promising solution for representing multiple languages in a single model. In this paper, we propose new criteria to…
Exploring Interpretability of Independent Components of Word Embeddings with Automated Word Intruder Test
Tomáš Musil, David Mareček
Independent Component Analysis (ICA) is an algorithm originally developed for finding separate sources in a mixed signal, such as a recording of multiple people in the same room sp…
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…
THEaiTRE 1.0: Interactive generation of theatre play scripts
Rudolf Rosa, Tomáš Musil, Ondřej Dušek +13
We present the first version of a system for interactive generation of theatre play scripts. The system is based on a vanilla GPT-2 model with several adjustments, targeting specif…
Measuring Memorization Effect in Word-Level Neural Networks Probing
Rudolf Rosa, Tomáš Musil, David Mareček
Multiple studies have probed representations emerging in neural networks trained for end-to-end NLP tasks and examined what word-level linguistic information may be encoded in the…