--- title: "An HMM Approach to Vowel Restoration in Arabic and Hebrew — Gal 2002" description: "Hebrew and Arabic are written without most vowels, so many words have several readings, and a native reader uses… 8 references, cited by 26 papers here." authors: ["Ya'akov Gal"] year: 2002 venue: "Proceedings of the ACL-02 Workshop on Computational Approaches to Semitic Languages" source: "https://aclanthology.org/W02-0504/" doi: "10.3115/1118637.1118641" licence: "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)" licence_url: "https://creativecommons.org/licenses/by-nc-sa/3.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/gal-2002-hmm-approach-vowel-restoration-arabic/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/gal-2002-hmm-approach-vowel-restoration-arabic/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2002](https://md.research.elamur.ai/free/en/papers/2002/) / An HMM Approach to Vowel Restoration in Arabic and Hebrew # An HMM Approach to Vowel Restoration in Arabic and Hebrew **Authors:** Ya'akov Gal · **Year:** 2002 · **Venue:** Proceedings of the ACL-02 Workshop on Computational Approaches to Semitic Languages **Link:** [aclanthology.org/W02-0504](https://aclanthology.org/W02-0504/) · library `aclbulk-2002-gal-hmm-approach-vowel-restoration-arabic` · **Licence:** [CC BY-NC-SA 3.0](https://creativecommons.org/licenses/by-nc-sa/3.0/) — summary only, never carried into a release [**80** citations](https://openalex.org/works?filter=cites:W2063116544) OpenAlex, 2026-10-14 · [**26** citations in our library](https://md.research.elamur.ai/free/en/papers/gal-2002-hmm-approach-vowel-restoration-arabic/cited-by/) of the 140,884 papers whose bibliographies we read · [Proceedings of the ACL-02 Workshop on Computational Approaches to Semitic Languages](https://aclanthology.org/volumes/W02-05/) · [licence](https://creativecommons.org/licenses/by-nc-sa/3.0/) - [Publisher's page](https://aclanthology.org/W02-0504/) - [PDF](https://aclanthology.org/W02-0504.pdf) - [DOI 10.3115/1118637.1118641](https://doi.org/10.3115/1118637.1118641) - [OpenAlex](https://openalex.org/W2063116544) **Authors (1)** 1. [Gal, Ya'akov](https://openalex.org/A5024303852) [ORCID](https://orcid.org/0000-0001-7187-8572) · [Semantic Scholar](https://www.semanticscholar.org/author/1721094) · h 29 · 2,844 citations · 188 works Citations and author metrics: OpenAlex, 2026-10-14; authors with the same name are not always told apart. ## What it is about Hebrew and Arabic are written without most vowels, so many words have several readings, and a native reader uses context to choose. Gal restores vowels with a bigram hidden Markov model: each hidden state is a fully vowelled word that emits its unvowelled form, transitions are bigram counts with Katz back-off and Good–Turing discounting, and Viterbi finds the best path. Training and testing use a Hebrew Bible text (about 300,000 words) and a transliterated Qur'an (about 90,000 words), with 10% held out. Word accuracy is 81% for Hebrew (87% for the phonetic group of each vowel) and 86% for Arabic, against unigram baselines of 68% and 74%. Most word errors come from words absent from the training data (11% in Hebrew, 8% in Arabic). ## Ideas - I2. Katz back-off for unseen bigrams: when a pair of segmented words is unseen in the counts, back off to the unigram estimate with a discounted mass, rather than scoring zero. This is a small deterministic scorer, with the counts in BTreeMaps. - I3. An "unseen word" state that emits the bare word with a fixed mass, rather than a guessed vowel pattern. Gal names morphological analysis as the next step for unseen words; the dictionary builder has no roots yet, so it is the place where that analysis would come from. ## For Mova - I1. Use the unigram baseline as the floor for `tools/hbo` in unpointed mode: any claim there must beat 68% on the same kind of held-out Hebrew split. Report the split and the word accuracy beside it. I1 and I2 go into `tools/hbo` (unpointed mode and its evaluation). I3 goes into [languages/hbo/10-lexicon.md](https://mova.elamur.ai/free/en/docs/languages/hbo/10-lexicon/), linked to the dictionary builder. ## Institutions [🎓**Harvard University** Cambridge · United States 64 works · 35,670 citations](https://md.research.elamur.ai/free/en/universities/harvard-university/) Topics[Hebrew & Aramaic](https://md.research.elamur.ai/free/en/topics/hebrew-aramaic/) · [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) ## Cite Cite as Ya'akov Gal. 2002. An HMM Approach to Vowel Restoration in Arabic and Hebrew. Proceedings of the ACL-02 Workshop on Computational Approaches to Semitic Languages. The paper itself, not this card. BibTeX from the library's record of the work. [DOI 10.3115/1118637.1118641](https://doi.org/10.3115/1118637.1118641) ```bibtex @inproceedings{gal2002hmm, title = {{An HMM Approach to Vowel Restoration in Arabic and Hebrew}}, author = {Ya'akov Gal}, booktitle = {Proceedings of the ACL-02 Workshop on Computational Approaches to Semitic Languages}, year = {2002}, doi = {10.3115/1118637.1118641}, url = {https://doi.org/10.3115/1118637.1118641} } ``` - [← previous The FrameNet Database and Software Tools](https://md.research.elamur.ai/free/en/papers/fillmore-2002-framenet-database-software-tools/) - [next → Bilingual FrameNet Dictionaries for Machine Translation](https://md.research.elamur.ai/free/en/papers/boas-2002-bilingual-framenet-dictionaries-machine-translation/) - [↑ back to papers of 2002](https://md.research.elamur.ai/free/en/papers/2002/) ## References 8 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Academy of the Hebrew Language 1957. “The rules for Hebrew-Latin transcription, ” In Memiors of the Academy of the Hebrew Language, pages 5-8 (in Hebrew) [find](https://scholar.google.com/scholar?q=Academy+of+the+Hebrew+Language+1957%2E+%E2%80%9CThe+rules+for+Hebrew%2DLatin+transcription%2C+%E2%80%9D+In+Memiors+of+the+Academy+of+the+Hebrew+Language%2C+pages+5%2D8+%28in+Hebrew%29) 2. Beesley, K. 1998. "Arabic finite-state morphological analysis and generation," in COLING-96 Proceedings 1 : 89-94, Copenhagen. [find](https://scholar.google.com/scholar?q=Beesley%2C+K%2E+1998%2E+%22Arabic+finite%2Dstate+morphological+analysis+and+generation%2C%22+in+COLING%2D96+Proceedings+1+%3A+89%2D94%2C+Copenhagen%2E) 3. Charniak, E. 1995. Statistical Language Learning, MIT Press. [find](https://scholar.google.com/scholar?q=Charniak%2C+E%2E+1995%2E+Statistical+Language+Learning%2C+MIT+Press%2E) 4. Choueka, Y. and Neeman, Y. 1995. “Nakdan-Text, (an In-Context Text-Vocalizer for Modern Hebrew),” BISFAI-95, The Fifth Bar Ilan Symposium for Artificial Intelligence Dagan, D., Pereira P., and Lee L. 1994. “Similarity-based estimation of word cooccurrence probabilities, ” In Proceedings of the 32nd Annual Meeting of the Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Choueka%2C+Y%2E+and+Neeman%2C+Y%2E+1995%2E+%E2%80%9CNakdan%2DText%2C+%28an+In%2DContext+Text%2DVocalizer+for+Modern+Hebrew%29%2C%E2%80%9D+BISFAI%2D95%2C+The+Fifth+Bar+Ilan+Symposium+for+Artificial+Intelligence+Dagan%2C+D%2E%2C+Pereira+P%2E%2C+and+Lee+L%2E+) 5. Gale, W. A. and Sampson, G. 1995. “Good-Turing Frequency Estimation Without Tears,” Journal of Quantitative Linguistics 2, 217-237. Katz, S., “Estimation of probabilities from sparse data for the language model component of a speech recognizer, ” In IEEE Transactions on Acoustics, Speech, and Signal Processing. [find](https://scholar.google.com/scholar?q=Gale%2C+W%2E+A%2E+and+Sampson%2C+G%2E+1995%2E+%E2%80%9CGood%2DTuring+Frequency+Estimation+Without+Tears%2C%E2%80%9D+Journal+of+Quantitative+Linguistics+2%2C+217%2D237%2E+Katz%2C+S%2E%2C+%E2%80%9CEstimation+of+probabilities+from+sparse+data+for+the+lang) 6. Kontorovich L.and Lee D. 2001. “Problems in Semitic NLP,” NIPS Workshop on Machine Learning Methods for Text and Images Levinger, M., Ornan U., Itai A. 1995. “Learning Morpho-Lexical Probabilities from an Untagged Corpus with an Application to Hebrew, ” Computational Linguistics, 21(3): 383-404 [our card](https://md.research.elamur.ai/free/en/papers/levinger-1995-learning-morpho-lexical-probabilities-untagged/) 7. Segel, A. 1997. “A probabilistic Morphological Analyzer for Hebrew undotted text,” MSc thesis, Israeli Institute of Technology, Technion. (in Hebrew) [find](https://scholar.google.com/scholar?q=Segel%2C+A%2E+1997%2E+%E2%80%9CA+probabilistic+Morphological+Analyzer+for+Hebrew+undotted+text%2C%E2%80%9D+MSc+thesis%2C+Israeli+Institute+of+Technology%2C+Technion%2E+%28in+Hebrew%29) 8. Westminster Theological Seminar 1998. "The Hebrew Morphological Database", Philadelphia, PA [find](https://scholar.google.com/scholar?q=Westminster+Theological+Seminar+1998%2E+%22The+Hebrew+Morphological+Database%22%2C+Philadelphia%2C+PA)