Publications

Google Scholar

2025

Memorisation meets compositionality in natural language processing
Verna Dankers
PhD thesis, University of Edinburgh
Thesis

Memorization Inheritance in Sequence-Level Knowledge Distillation for Neural Machine Translation
Verna Dankers, Vikas Raunak
In ACL
Paper

2024

Evaluating subword tokenization: Alien subword composition and OOV generalization challenge
Khuyagbaatar Batsuren, Ekaterina Vylomova, Verna Dankers, Tsetsuukhei Delgerbaatar, Omri Uzan, Yuval Pinter, Gábor Bella
Preprint
Paper

Generalisation First, Memorisation Second? Memorisation Localisation for Natural Language Classification Tasks
Verna Dankers, Ivan Titov
In ACL Findings
Paper

2023

A taxonomy and review of generalization research in NLP
Dieuwke Hupkes, Mario Giulianelli, Verna Dankers, Mikel Artetxe, Yanai Elazar, Tiago Pimentel, Christos Christodoulopoulos, Karim Lasri, Naomi Saphra, Arabella Sinclair, Dennis Ulmer, Florian Schottmann, Khuyagbaatar Batsuren, Kaiser Sun, Koustuv Sinha, Leila Khalatbari, Maria Ryskina, Rita Frieske, Ryan Cotterell, Zhijing Jin
In Nature Machine Intelligence, volume 5, pages 1161–1174
Paper

Paper Bullets: Modeling Propaganda with the Help of Metaphor
Daniel Baleato Rodríguez, Verna Dankers, Preslav Nakov, Ekaterina Shutova
In Findings of EACL, pages 472–489
Paper

Memorisation cartography: mapping out the memorisation-generalisation continuum in neural machine translation
Verna Dankers, Ivan Titov, Dieuwke Hupkes
In EMNLP, pages 8323–8343
Paper

Latent Feature-based Data Splits to Improve Generalisation Evaluation: A Hate Speech Detection Case Study
Maike Zöfle, Verna Dankers, Ivan Titov
In Proceedings of the 1st GenBench Workshop on (Benchmarking) Generalisation in NLP, pages 112–129
Paper

Non-compositionality in sentiment: new data and analyses
Verna Dankers, Christopher G. Lucas
In Findings of EMNLP, pages 5150–5162
Paper

2022

Meta-learning for fast cross-lingual adaptation in dependency parsing
Anna Langedijk, Verna Dankers, Phillip Lippe, Sander Bos, Bryan Cardenas Guevara, Helen Yannakoudakis, Ekaterina Shutova
In ACL (Long Papers)
Paper

Recursive Neural Networks with Bottlenecks Diagnose (Non-)Compositionality
Verna Dankers, Ivan Titov
In Findings of EMNLP, pages 4361–4378
Paper

Can Transformer be Too Compositional? Analysing Idiom Processing in Neural Machine Translation
Verna Dankers, Christopher Lucas, Ivan Titov
In ACL (Long Papers), pages 3608–3626
Paper

The Paradox of the Compositionality of Natural Language: A Neural Machine Translation Case Study
Verna Dankers, Elia Bruni, Dieuwke Hupkes
In ACL (Long Papers), pages 4154–4175
Paper

2021

Generalising to German Plural Noun Classes, from the Perspective of a Recurrent Neural Network
Verna Dankers*, Anna Langedijk*, Kate McCurdy, Adina Williams, Dieuwke Hupkes (*equal contribution)
In CoNLL, pages 94–108 — 🏅 Best paper award
Paper

Episodic memory demands modulate novel metaphor use during event narration
Vesna G. Djokic, Verna Dankers, Ekaterina Shutova
In Proceedings of the Annual Meeting of the Cognitive Science Society, 43(43)
Paper

2020

Compositionality Decomposed: How do Neural Networks Generalise?
Dieuwke Hupkes, Verna Dankers, Mathijs Mul, Elia Bruni
In Journal of Artificial Intelligence Research, 67, pages 757–795
Paper IJCAI extended abstract

The Pragmatics behind Politics: Modelling Metaphor, Framing and Emotion in Political Discourse
Pere-Lluis Huguet Cabot, Verna Dankers, David Abadi, Agneta Fischer, Ekaterina Shutova
In Findings of EMNLP, pages 4479–4488
Paper Code

Being neighbourly: Neural metaphor identification in discourse
Verna Dankers, Karan Malhotra, Gaurav Kudva, Volodymyr Medentsiy, Ekaterina Shutova
In Proceedings of the Second Workshop on Figurative Language Processing, pages 227–234
Paper Code

2019

Modelling the interplay of metaphor and emotion through multitask learning
Verna Dankers, Marek Rei, Martha Lewis, Ekaterina Shutova
In EMNLP-IJCNLP, pages 2218–2229
Paper

Transcoding compositionally: Using attention to find more generalisable solutions
Kris Korrel, Dieuwke Hupkes, Verna Dankers, Elia Bruni
In BlackboxNLP @ ACL, pages 1–11
Paper Code

2017

Modelling word associations with word embeddings for a guesser agent in the Taboo city challenge competition
Verna Dankers, Aysenur Bilgin, Raquel Fernández
In ESSENCE Workshop @ IJCAI-2017
Paper

Modelling the generation and retrieval of word associations with word embeddings
Verna Dankers, Aysenur Bilgin, Raquel Fernández
In BNAIC, pages 401–402
Abstract

Modelling word associations and interactiveness for describer agents in word-guessing games
Verna Dankers, Aysenur Bilgin, Raquel Fernández
In BNAIC, pages 408–409
Abstract