| Challenge: | Abugidas are writing systems where consonant letters represent syllables with a default vowel and other vowels are denoted by diacritics. |
| Approach: | They investigated the feasibility of recovering the original text written in an abugida after omitting subordinate diacritics and merging consonant letters with similar phonetic values. |
| Outcome: | The proposed method recovers the original text written in an abugida with 94% - 97% accuracy at the top-1 level and 98% - 99% at the bottom-4 level even after omitting most diacritics and merging the remaining 30 - 50 characters into 21 graphemes. |
Similar Papers
Diacritics Restoration Using Neural Networks (L18-1)
Copied to clipboard
| Challenge: | a novel combination of character-level recurrent neural network and language model is proposed . people often replace characters with diacritics with their ASCII counterparts . |
| Approach: | They propose a character-level recurrent neural network-based model and a language model for diacritics restoration. |
| Outcome: | The proposed model reduces error of current best systems by 20% to 64% on four languages . it is also able to restore diacritical marks on a number of languages using the same model . |
Highly Effective Arabic Diacritization using Sequence to Sequence Modeling (N19-1)
Copied to clipboard
| Challenge: | Arabic text is written without short vowels (or diacritics) their presence is essential for properly verbalizing Arabic . |
| Approach: | They propose a character-level sequence-to-sequence deep learning model that recovers both types of diacritics without the use of explicit feature engineering. |
| Outcome: | The proposed model outperforms all previous state-of-the-art models on overlapping windows of words . it achieves a word error rate (WER) of 4.49% compared to the state- of-the art systems . |
A Multitask Learning Approach for Diacritic Restoration (2020.acl-main)
Copied to clipboard
| Challenge: | Diacritics are used to specify pronunciations and meanings in many languages like Arabic. |
| Approach: | They propose to use multi-task learning to optimize diacritic restoration with related NLP problems . they use Arabic as a case study since it has sufficient data resources for tasks . |
| Outcome: | The proposed model outperforms baseline models and is comparable to the state-of-the-art models. |
Consonant is all you need: a compact representation of English text for efficient NLP (2023.findings-emnlp)
Copied to clipboard
| Challenge: | In natural language processing, the representation of text plays a crucial role in various tasks such as language modeling, sentiment analysis, and machine translation. |
| Approach: | They propose a method to represent English text with only consonants that is more discriminative than vowels and a technique to retrieve vowel information from it. |
| Outcome: | The proposed representation significantly reduces the overall memory and compute footprint required for storing and processing textual data. |
PunKtuator: A Multilingual Punctuation Restoration System for Spoken and Written Text (2021.eacl-demos)
Copied to clipboard
| Challenge: | Prior punctuation restoration methods have focused on using lexical features, prosodic features or combination of both. |
| Approach: | They propose a multitask modeling approach to restore punctuation in multiple high resource languages using acoustic models and a computational model. |
| Outcome: | The proposed system can restore punctuation in Germanic, Romanic and low resource languages without extensive knowledge of grammar or syntax. |
Recovering Missing Characters in Old Hawaiian Writing (D18-1)
Copied to clipboard
| Challenge: | Modern Hawaiian orthography includes characters for long vowels and glottal stops . manual transliteration is laborious when performed manually . |
| Approach: | They propose two methods to help transliterate Hawaiian between older and newer texts automatically using finite state transducers and a recurrent neural network language model. |
| Outcome: | The proposed method solves the transliteration problem automatically using finite state transducers and a neural network language model. |
Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: System Demonstrations (2020.aacl-demo)
Copied to clipboard
| Challenge: | AACL-IJCNLP 2020 demos track invited submissions ranging from early prototypes to mature production-ready systems. |
| Approach: | the AACL-IJCNLP 2020 demonstrations track invited submissions . the submissions ranged from early prototypes to mature production-ready systems . |
| Outcome: | the AACL-IJCNLP 2020 demonstrations track received 13 submissions this year . the acceptance rate was 54%) . |
CaMEL: Case Marker Extraction without Labels (2022.acl-long)
Copied to clipboard
| Challenge: | Existing models for morphological case marking and semantic content are not isomorphic. |
| Approach: | They propose a model that extracts case markers from a multilingual corpus using a noun phrase chunker and an alignment system. |
| Outcome: | The proposed model can extract case markers in 83 languages and visualise similarities and differences between case systems and annotate fine-grained deep cases in languages where they are not overtly marked. |
Advancing Arabic Diacritization: Improved Datasets, Benchmarking, and State-of-the-Art Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Arabic diacritics are typically omitted in written Arabic, leading to ambiguity . authors propose a methodology to analyze and refine a large diacritized corpus . |
| Approach: | They propose a methodology to analyze and refine a large diacritized corpus to improve training quality. |
| Outcome: | The proposed model achieves state-of-the-art results with 3.12% and 2.70% WER on WikiNews-2014 and Wikinews-2024. |
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: System Demonstrations (2022.aacl-demo)
Copied to clipboard
| Challenge: | the AACL-IJCNLP 2022 demonstrations track invited submissions ranging from early research prototypes to mature production-ready systems. |
| Approach: | the system demonstrations track invited submissions from early research prototypes to mature production-ready systems. |
| Outcome: | the AACL-IJCNLP 2022 demonstrations track received 17 submissions this year . the acceptance rate was 58.8% . |