mlsanityData to 14 Oct 2026

Improving Arabic Diacritization by Learning to Diacritize and Translate

arXiv 2109.14150 ↗First posted 29 Sep 2021cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

We propose a novel multitask learning method for diacritization which trains a model to both diacritize and translate. Our method addresses data sparsity by exploiting large, readily available bitext corpora. Furthermore, translation requires implicit linguistic and semantic knowledge, which is helpful for resolving ambiguities in the diacritization task. We apply our method to the Penn Arabic Treebank and report a new state-of-the-art word error rate of 4.79%. We also conduct manual and automatic analysis to better understand our method and highlight some of the remaining challenges in diacritization.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 23 of its 45 references that are in the map. First posted on arXiv 29 Sep 2021.

Builds on

23 of 45 references.

References · 23

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  3. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,989
  4. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,488
  5. 2019Mitigating Gender Bias in Natural Language Processing: Literature Reviewcited by 287
  6. 2019WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipediacited by 223
  7. 2016Transfer Learning for Low-Resource Neural Machine Translationcited by 188
  8. 2019CCAligned: A Massive Collection of Cross-Lingual Web-Document Pairscited by 136
  9. 2020Automatic Machine Translation Evaluation in Many Languages via Zero-Shot Paraphrasingcited by 115
  10. 2018Rapid Adaptation of Neural Machine Translation to New Languagescited by 82
  11. 2018On the Impact of Various Types of Noise on Neural Machine Translationcited by 76
  12. 2017Transfer Learning across Low-Resource, Related Languages for Neural Machine Translationcited by 58
11 more
  1. 2016Fully Character-Level Neural Machine Translation without Explicit Segmentationcited by 55
  2. 2018Revisiting Character-Based Neural Machine Translation with Capacity and Compressioncited by 28
  3. 2021ZEN 2.0: Continue Training and Adaption for N-gram Enhanced Text Encoderscited by 22
  4. 2019Arabic Text Diacritization Using Deep Neural Networkscited by 18
  5. 2019Joint Diacritization, Lemmatization, Normalization, and Fine-Grained Morphological Taggingcited by 12
  6. 2020A Multitask Learning Approach for Diacritic Restorationcited by 12
  7. 2013LDC Arabic Treebanks and Associated Corpora: Data Divisions Manualcited by 11
  8. 2019Adversarial Multitask Learning for Joint Multi-Feature and Multi-Dialect Morphological Modelingcited by 9
  9. 2019Efficient Convolutional Neural Networks for Diacritic Restorationcited by 9
  10. 2021Diacritics Restoration using BERT with Analysis on Czech languagecited by 6
  11. 2019Homograph Disambiguation Through Selective Diacritic Restorationcited by 5

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 4.

6 papers.

  1. 2024Arabic Diacritics in the Wild: Exploiting Opportunities for Improved Diacritizationcited by 8
  2. 2024Arabic Text Diacritization In The Age Of Transfer Learning: Token Classification Is All You Needcited by 4
  3. 2023Take the Hint: Improving Arabic Diacritization with Partially-Diacritized Textcited by 2
  4. 2023Multilingual context-based pronunciation learning for Text-to-Speechcited by 2
  5. 2024Interplay of Machine Translation, Diacritics, and Diacritizationcited by 1
  6. 2024Acquiring Pronunciation Knowledge from Transcribed Speech Audio via Multi-task Learningcited by 1