Effective multi-dialectal arabic POS tagging. (14th November 2020)

• Record Type: Journal Article
• Authors: Darwish, Kareem; Attia, Mohammed; Mubarak, Hamdy; Samih, Younes; Abdelali, Ahmed; Màrquez, Lluís; Eldesouki, Mohamed; Kallmeyer, Laura
• Editors: Zampieri, Marcos; Nakov, Preslav
• Is Part Of: Natural language engineering. Volume 26:Part 6(2020)
• Page Start: 677
• Page End: 690
• Publication Date: 2020-11-14
• Subjects: Part-of-speech tagging, -- Arabic, -- Dialects, -- Deep neural network, -- Brown clusters; Natural language processing (Computer science) -- Periodicals; Software engineering -- Periodicals; 006.35
• DOI: 10.1017/S1351324920000078
• Languages: English
• ISSNs: 1351-3249

Abstract

Abstract: This work introduces robust multi-dialectal part of speech tagging trained on an annotated data set of Arabic tweets in four major dialect groups: Egyptian, Levantine, Gulf, and Maghrebi. We implement two different sequence tagging approaches. The first uses conditional random fields (CRFs), while the second combines word- and character-based representations in a deep neural network with stacked layers of convolutional and recurrent networks with a CRF output layer. We successfully exploit a variety of features that help generalize our models, such as Brown clusters and stem templates. Also, we develop robust joint models that tag multi-dialectal tweets and outperform uni-dialectal taggers. We achieve a combined accuracy of 92.4% across all dialects, with per dialect results ranging between 90.2% and 95.4%. We obtained the results using a train/dev/test split of 70/10/20 for a data set of 350 tweets per dialect.