Given the lack of resources for Arabic dialects, the construction of corpora, lexical resources, and tools is a non-trivial challenge. The focus of the article is to describe our in-progress work to address these deficiencies. We start with Moroccan and Tunisian dialects to provide annotated corpora and corpus-based lexical resources. We also aim to extend an existing morphological engine with linguistic resources built ad hoc for each dialect. In addition, we develop an integrated component in the morphological engine to better address linguistic and sociolinguistic characteristics while preserving the integrity of dialectal texts.
Challenges and Progress in Constructing Arabic Dialect Corpora and Linguistic tools: A Focus on Moroccan and Tunisian Dialects / Nahli, O., Gugliotta, E., Khlif, N., Giulia, B.. - (2023), pp. 293-298. [10.1109/cist56084.2023.10410009]
Challenges and Progress in Constructing Arabic Dialect Corpora and Linguistic tools: A Focus on Moroccan and Tunisian Dialects
Gugliotta, Elisa;
2023-01-01
Abstract
Given the lack of resources for Arabic dialects, the construction of corpora, lexical resources, and tools is a non-trivial challenge. The focus of the article is to describe our in-progress work to address these deficiencies. We start with Moroccan and Tunisian dialects to provide annotated corpora and corpus-based lexical resources. We also aim to extend an existing morphological engine with linguistic resources built ad hoc for each dialect. In addition, we develop an integrated component in the morphological engine to better address linguistic and sociolinguistic characteristics while preserving the integrity of dialectal texts.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
