no code implementations • 15 May 2024 • Dylan Phelps, Thomas Pickard, Maggie Mi, Edward Gow-Smith, Aline Villavicencio
In particular, how well do such models perform in comparison to encoder-only models fine-tuned specifically for idiomaticity tasks?
no code implementations • 14 May 2024 • Agne Knietaite, Adam Allsebrook, Anton Minkov, Adam Tomaszewski, Norbert Slinko, Richard Johnson, Thomas Pickard, Dylan Phelps, Aline Villavicencio
Compositionality in language models presents a problem when processing idiomatic expressions, as their meaning often cannot be directly derived from their individual parts.
no code implementations • 15 Jan 2024 • Edward Gow-Smith, Dylan Phelps, Harish Tayyar Madabushi, Carolina Scarton, Aline Villavicencio
As such, removing these symbols has been shown to have a beneficial effect on the processing of morphologically complex words for transformer encoders in the pretrain-finetune paradigm.
no code implementations • LREC (MWE) 2022 • Dylan Phelps, Xuan-Rui Fan, Edward Gow-Smith, Harish Tayyar Madabushi, Carolina Scarton, Aline Villavicencio
In particular we study the impact of Pattern Exploit Training (PET), a few-shot method of classification, and BERTRAM, an efficient method of creating contextual embeddings, on the task of idiomaticity detection.
no code implementations • SemEval (NAACL) 2022 • Dylan Phelps
This paper describes our system for SemEval-2022 Task 2 Multilingual Idiomaticity Detection and Sentence Embedding sub-task B.