logo Idiap Research Institute        
 [BibTeX] [Marc21]
Multilingual Extraction and Categorization of Lexical Collocations with Graph-aware Transformers
Type of publication: Conference paper
Citation: Anke_*SEM2022_2022
Publication status: Published
Booktitle: Proceedings of the 11th Joint Conference on Lexical and Computational Semantics
Year: 2022
Month: July
Pages: 89–100
Location: Seattle, USA
Abstract: 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.
Projects Idiap
Authors Anke, Luis Espinosa
Shvets, Alexander
Mohammadshahi, Alireza
Henderson, James
Wanner, Leo
Added by: [UNK]
Total mark: 0
  • Anke_*SEM2022_2022.pdf