Generalisation First, Memorisation Second? Memorisation Localisation for Natural Language Classification Tasks Verna Dankers, Ivan Titov
In ACL Findings [paper]
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]
Memorisation cartography: mapping out the memorisation-generalisation continuum in neural machine translation Verna Dankers, Ivan Titov, Dieuwke Hupkes
In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 8323-8343 [paper]
Non-compositionality in sentiment: new data and analyses Verna Dankers, Christopher G. Lucas
In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 5150-5162 [paper]
Recursive Neural Networks with Bottlenecks Diagnose (Non-)Compositionality Verna Dankers, Ivan Titov
In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 4361-4378 [paper]
Can Transformer be Too Compositional? Analysing Idiom Processing in Neural Machine Translation Verna Dankers, Christopher Lucas, Ivan Titov
In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: 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 Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4154-4175 [paper]
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 Proceedings of the 25th Conference on Computational Natural Language Learning, pages 94-108 [paper]
🏅Best paper award.
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]
Compositionality Decomposed: How do Neural Networks Generalise?
Dieuwke Hupkes, Verna Dankers, Mathijs Mul, and Elia Bruni
In Journal of Artificial Intelligence Research, 67, pages 757-795
[paper] [extended abstract (IJCAI)]
The Pragmatics behind Politics: Modelling Metaphor, Framing and Emotion in Political Discourse
Pere-Lluis Huguet Cabot, Verna Dankers, David Abadi, Agneta Fischer and Ekaterina Shutova
In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4479-4488
[paper] [source code]
Being neighbourly: Neural metaphor identification in discourse Verna Dankers, Karan Malhotra, Gaurav Kudva, Volodymyr Medentsiy and Ekaterina Shutova
In Proceedings of the Second Workshop on Figurative Language Processing, pages 227-234
[paper] [source code]
Modelling the interplay of metaphor and emotion through multitask learning Verna Dankers, Marek Rei, Martha Lewis, and Ekaterina Shutova
In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 2218-2229
[paper]
Transcoding compositionally: Using attention to find more generalisable solutions
Kris Korrel, Dieuwke Hupkes, Verna Dankers, and Elia Bruni
In Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 1-11 [paper] [source code]
Modelling word associations with word embeddings for a guesser agent in the Taboo city challenge competition Verna Dankers, Aysenur Bilgin, and Raquel Fernández
In The 6th ESSENCE Workshop: the Taboo city challenge competition @ IJCAI-2017 [paper]
Modelling the generation and retrieval of word associations with word embeddings Verna Dankers, Aysenur Bilgin, and Raquel Fernández
In Proceedings of the 29th Benelux Conference on Artificial Intelligence (BNAIC), pages 401-402 [abstract]
Modelling word associations and interactiveness for describer agents in word-guessing games Verna Dankers, Aysenur Bilgin, and Raquel Fernández
In Proceedings of the 29th Benelux Conference on Artificial Intelligence (BNAIC), pages 408-409 [abstract]