Friday 3rd October 2025 - 11am, Johan Bos (University of Groningen) Speaker: Professor Johan Bos (Computational Semantics, University of Groningen)Title: Neural Semantic Parsing with Extremely Rich Symbolic Meaning Representations Abstract: Current open-domain neural semantics parsers show impressive performance. However, closer inspection of the symbolic meaning representations they produce reveals significant weaknesses: Sometimes they tend to merely copy character sequences from the source text to form symbolic concepts, defaulting to the most frequent word sense based in the training distribution. By leveraging the hierarchical structure of a lexical ontology, we introduce a novel compositional symbolic representation for concepts based on their position in the taxonomical hierarchy. This representation provides richer semantic information and enhances interpretability. We introduce a neural “taxonomical” semantic parser to utilize this new representation system of predicates, and compare it with a standard neural semantic parser trained on the traditional meaning representation format, employing a novel challenge set and evaluation metric for evaluation. Is this taxonomical model, trained on much richer and complex meaning representations, better than the traditional model using the standard metrics for evaluation, and is able to learn the taxonomical hierarchy? Oct 03 2025 11.00 - 12.00 Friday 3rd October 2025 - 11am, Johan Bos (University of Groningen) This event is co-organised by ILCC and by the UKRI Centre for Doctoral Training in Natural Language Processing, https://nlp-cdt.ac.uk. IF, G.03
Friday 3rd October 2025 - 11am, Johan Bos (University of Groningen) Speaker: Professor Johan Bos (Computational Semantics, University of Groningen)Title: Neural Semantic Parsing with Extremely Rich Symbolic Meaning Representations Abstract: Current open-domain neural semantics parsers show impressive performance. However, closer inspection of the symbolic meaning representations they produce reveals significant weaknesses: Sometimes they tend to merely copy character sequences from the source text to form symbolic concepts, defaulting to the most frequent word sense based in the training distribution. By leveraging the hierarchical structure of a lexical ontology, we introduce a novel compositional symbolic representation for concepts based on their position in the taxonomical hierarchy. This representation provides richer semantic information and enhances interpretability. We introduce a neural “taxonomical” semantic parser to utilize this new representation system of predicates, and compare it with a standard neural semantic parser trained on the traditional meaning representation format, employing a novel challenge set and evaluation metric for evaluation. Is this taxonomical model, trained on much richer and complex meaning representations, better than the traditional model using the standard metrics for evaluation, and is able to learn the taxonomical hierarchy? Oct 03 2025 11.00 - 12.00 Friday 3rd October 2025 - 11am, Johan Bos (University of Groningen) This event is co-organised by ILCC and by the UKRI Centre for Doctoral Training in Natural Language Processing, https://nlp-cdt.ac.uk. IF, G.03
Oct 03 2025 11.00 - 12.00 Friday 3rd October 2025 - 11am, Johan Bos (University of Groningen) This event is co-organised by ILCC and by the UKRI Centre for Doctoral Training in Natural Language Processing, https://nlp-cdt.ac.uk.
