1 code implementation • COLING 2022 • Wessel Poelman, Rik van Noord, Johan Bos
Even though many recent semantic parsers are based on deep learning methods, we should not forget that rule-based alternatives might offer advantages over neural approaches with respect to transparency, portability, and explainability.
no code implementations • SemEval (NAACL) 2022 • Wessel Poelman, Gijs Danoe, Esther Ploeger, Frank van den Berg, Tommaso Caselli, Lukas Edman
This paper describes our system created for the SemEval 2022 Task 3: Presupposed Taxonomies - Evaluating Neural-network Semantics.
no code implementations • 14 Sep 2023 • Mahdi Dhaini, Wessel Poelman, Ege Erdogan
While recent advancements in the capabilities and widespread accessibility of generative language models, such as ChatGPT (OpenAI, 2022), have brought about various benefits by generating fluent human-like text, the task of distinguishing between human- and large language model (LLM) generated text has emerged as a crucial problem.
1 code implementation • 6 Feb 2024 • Esther Ploeger, Wessel Poelman, Miryam de Lhoneux, Johannes Bjerva
We recommend future work to include an operationalization of 'typological diversity' that empirically justifies the diversity of language samples.