Automatic diacritization of Arabic text using recurrent neural networks

@article{Abandah2015AutomaticDO,
  title={Automatic diacritization of Arabic text using recurrent neural networks},
  author={Gheith A. Abandah and Alex Graves and Balkees Al-Shagoor and Alaa Arabiyat and Fuad T. Jamour and Majid A. Al-Taee},
  journal={International Journal on Document Analysis and Recognition (IJDAR)},
  year={2015},
  volume={18},
  pages={183-197}
}
This paper presents a sequence transcription approach for the automatic diacritization of Arabic text. A recurrent neural network is trained to transcribe undiacritized Arabic text with fully diacritized sentences. We use a deep bidirectional long short-term memory network that builds high-level linguistic abstractions of text and exploits long-range context in both input directions. This approach differs from previous approaches in that no lexical, morphological, or syntactical analysis is… CONTINUE READING
Highly Cited
This paper has 32 citations. REVIEW CITATIONS

From This Paper

Figures, tables, results, and topics from this paper.

Key Quantitative Results

  • Nonetheless, when the network is post-processed with our error correction techniques, it achieves state-of-the-art performance, yielding an average diacritic and word error rates of 2.09 and 5.82 %, respectively, on samples from 11 books.

Citations

Publications citing this paper.
Showing 1-10 of 24 extracted citations

Hybrid LSTM/MaxEnt Networks for Arabic Syntactic Diacritics Restoration

IEEE Signal Processing Letters • 2018
View 13 Excerpts
Highly Influenced

Diacritization Using Recurrent Neural Networks

Saba Amin Al - Qudah, Dr. Gheith Ali Abandah
2017
View 15 Excerpts
Highly Influenced

Diacritics Restoration Using Deep Neural Networks

2018 World Symposium on Digital Intelligence for Systems and Machines (DISA) • 2018

Diacritization of a Highly Cited Text: A Classical Arabic Book as a Case

2018 IEEE 2nd International Workshop on Arabic and Derived Script Analysis and Recognition (ASAR) • 2018
View 1 Excerpt

References

Publications referenced by this paper.
Showing 1-10 of 38 references

Tanzil - Quran Navigator. http://tanzil.net/download

H. Zarrabi-Zadeh
Last accessed on Nov • 2014
View 4 Excerpts
Highly Influenced

Bidirectional recurrent neural networks

IEEE Trans. Signal Processing • 1997
View 12 Excerpts
Highly Influenced

Long Short-Term Memory

Neural Computation • 1997
View 14 Excerpts
Highly Influenced

A first approach to the evaluation of arabic diacritization systems

Seventh International Conference on Digital Information Management (ICDIM 2012) • 2012
View 3 Excerpts
Highly Influenced

Buckwalter Arabic Morphological Analyzer, v2.0

T. Buckwalter
edn. Linguistic Data Consortium, Philadelphia • 2004
View 3 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…