Multilingual extraction and categorization of lexical collocations with graph-aware transformers
Multilingual extraction and categorization of lexical collocations with graph-aware transformers
Citació
- Espinosa Anke L, Shvets A, Mohammadshahi A, Henderson J, Wanner L. Multilingual extraction and categorization of lexical collocations with graph-aware transformers. In: Nastase V, Pavlick E, Taher Pilehvar M, Camacho-Collados J, Raganato A, editors. The 11th Joint Conference on Lexical and Computational Semantics (SEM 2022): proceedings of the Conference; 2022 Jul 14-15; Seattle, United States. Stroudsburg: ACL; 2022. p. 89-100. DOI: 10.18653/v1/2022.starsem-1.8
Enllaç permanent
Descripció
Dades relacionades
Resum
Recognizing and categorizing lexical collocations in context is useful for language learning, dictionary compilation and downstream NLP. However, it is a challenging task due to the varying degrees of frozenness lexical collocations exhibit. In this paper, we put forward a sequence tagging BERT-based model enhanced with a graph-aware transformer architecture, which we evaluate on the task of collocation recognition in context. Our results suggest that explicitly encoding syntactic dependencies in the model architecture is helpful, and provide insights on differences in collocation typification in English, Spanish and French.Descripció
Comunicació presentada a 11th Joint Conference on Lexical and Computational Semantics (SEM 2022), celebrat del 14 al 15 de juliol de 2022 a Seattle, Estats Units.