DeepAI AI Chat
Log In Sign Up

Deep Diacritization: Efficient Hierarchical Recurrence for Improved Arabic Diacritization

by   Badr AlKhamissi, et al.

We propose a novel architecture for labelling character sequences that achieves state-of-the-art results on the Tashkeela Arabic diacritization benchmark. The core is a two-level recurrence hierarchy that operates on the word and character levels separately—enabling faster training and inference than comparable traditional models. A cross-level attention module further connects the two, and opens the door for network interpretability. The task module is a softmax classifier that enumerates valid combinations of diacritics. This architecture can be extended with a recurrent decoder that optionally accepts priors from partially diacritized text, which improves results. We employ extra tricks such as sentence dropout and majority voting to further boost the final result. Our best model achieves a WER of 5.34 outperforming the previous state-of-the-art with a 30.56 reduction.


An Efficient Language-Independent Multi-Font OCR for Arabic Script

Optical Character Recognition (OCR) is the process of extracting digitiz...

Diacritization of Maghrebi Arabic Sub-Dialects

Diacritization process attempt to restore the short vowels in Arabic wri...

Adapting MARBERT for Improved Arabic Dialect Identification: Submission to the NADI 2021 Shared Task

In this paper, we tackle the Nuanced Arabic Dialect Identification (NADI...

AraDIC: Arabic Document Classification using Image-Based Character Embeddings and Class-Balanced Loss

Classical and some deep learning techniques for Arabic text classificati...

Arabic Diacritic Recovery Using a Feature-Rich biLSTM Model

Diacritics (short vowels) are typically omitted when writing Arabic text...

A Hybrid NN/HMM Modeling Technique for Online Arabic Handwriting Recognition

In this work we propose a hybrid NN/HMM model for online Arabic handwrit...

Phonetic and Visual Priors for Decipherment of Informal Romanization

Informal romanization is an idiosyncratic process used by humans in info...