2024/04/19 by Xiao Zhang, Zhang, Xiao, Gosse Bouma +3 · 3 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2404.12698
openalex publication_date 2024/04/19 · openalex created_date 2024/04/23 · openalex updated_date 2026/07/28
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. Our experimental findings demonstrate that the taxonomical model, trained on much richer and complex meaning representations, is slightly subordinate in performance to the traditional model using the standard metrics for evaluation, but outperforms it when dealing with out-of-vocabulary concepts. This finding is encouraging for research in computational semantics that aims to combine data-driven distributional meanings with knowledge-based symbolic representations.