activity
20192026
most citedEvaluating Subword Tokenization: Alien Subword Composition and OOV Generalization Challenge

6 citations · 10 across the 9 of their papers we have counts for

collaborators
Showing cs.CLShow all

11 papers · 1 filter

cs.CL2026

Leveraging Routing Dynamics in Mixture-of-Experts Models for Efficient Language Adaptation

Aditi Khandelwal, Marius Mosbach, Verna Dankers +2

Mixture-of-Experts (MoE) models are widely used to scale language models, yet their expert routing behavior and adaptation in a multilingual setting remain underexplored. In this w…

cs.CL2025

Memorization Inheritance in Sequence-Level Knowledge Distillation for Neural Machine Translation

Verna Dankers, Vikas Raunak

In this work, we explore how instance-level memorization in the teacher Neural Machine Translation (NMT) model gets inherited by the student model in sequence-level knowledge disti…

cs.CL2024

Generalisation First, Memorisation Second? Memorisation Localisation for Natural Language Classification Tasks

Verna Dankers, Ivan Titov

Memorisation is a natural part of learning from real-world data: neural models pick up on atypical input-output combinations and store those training examples in their parameter sp…

cs.CL20246 cited

Evaluating Subword Tokenization: Alien Subword Composition and OOV Generalization Challenge

Khuyagbaatar Batsuren, Ekaterina Vylomova, Verna Dankers +4

The popular subword tokenizers of current language models, such as Byte-Pair Encoding (BPE), are known not to respect morpheme boundaries, which affects the downstream performance…

cs.CL2023

Latent Feature-based Data Splits to Improve Generalisation Evaluation: A Hate Speech Detection Case Study

Maike Züfle, Verna Dankers, Ivan Titov

With the ever-growing presence of social media platforms comes the increased spread of harmful content and the need for robust hate speech detection systems. Such systems easily ov…

cs.CL2023

Memorisation Cartography: Mapping out the Memorisation-Generalisation Continuum in Neural Machine Translation

Verna Dankers, Ivan Titov, Dieuwke Hupkes

When training a neural network, it will quickly memorise some source-target mappings from your dataset but never learn some others. Yet, memorisation is not easily expressed as a b…