Mova0.5 pre-release⌕
☰
home / docs / papers / authors / Nizar Habash

Nizar Habash

48 paper cards in Mova's library · 2000–2026

Nizar Habash wrote 48 of the papers Mova reads, in 2000–2026, most of them on Treebanks, Part-of-speech tagging, Dependency parsing; often with Owen Rambow, Salam Khalifa, Dima Taji.

OpenAlex · ORCID · h-index 57 · 12233 citations · 359 works — openalex, 2026-10-18

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology · ORCID

Topics: Treebanks 8 · Part-of-speech tagging 8 · Dependency parsing 5 · Machine translation 5 · Universal Dependencies 2

Ideas Mova took (1)

From the ideas ledger: an idea tried, kept or queued, or measured with no gain, and what it gave.

Papers

  1. Arabic Morphosyntactic Tagging and Dependency Parsing with Large Language Models (2026)
    The authors test whether instruction-tuned large language models can produce explicit Arabic grammatical analysis: 14 morphological features per token (part of speech, aspect, mood, voice, person, gender, number, case, state, four proclitics and one enclitic), and labelled CATiB dependency trees.
  2. Arabic Sentence Segmentation Across Genres and Punctuation Conditions (2026)
    Arabic sentence boundaries are hard to find because punctuation is sparse, inconsistent or absent in many texts, and clauses are often joined by conjunctions such as wa- and fa-.
  3. Do Diacritics Matter? Evaluating the Impact of Arabic Diacritics on Tokenization and LLM Benchmarks (2026)
    The paper asks how Arabic diacritics (vowel marks and related signs) change tokenization and the scores of large language models.
  4. Parsing Arabic Dialects Revisited: New Benchmarks, Models, and Insights (2026)
    The paper revisits dependency parsing of dialectal Arabic, a task with little progress since the mid-2000s.
  5. YallaMorph: A Benchmark for Evaluating Arabic Morphological Generation in Large Language Models (2026)
    YallaMorph is a benchmark of over 600,000 test instances for controlled Arabic morphological generation. The task gives a lemma, a part of speech, a gloss and a feature bundle, and the model must produce the surface form, or say that the configuration is invalid. Items cover verbs (active and passive, perfective and…
  6. A Derivational ChainBank for Modern Standard Arabic (2025)
    The paper builds a derivational resource for Modern Standard Arabic: for each root, a tree that links every derived lemma (masdar, active and passive participles, nouns of place, adjectives in -iy, and so on) to its base, through a network of abstract patterns.
  7. Lemmatization as a Classification Task: Results from Arabic across Multiple Genres (2025)
    Arabic lemmatization is hard because the orthography drops vowels, so one written word has several lemma, POS and gloss readings.
  8. Computational Morphology and Lexicography Modeling of Modern Standard Arabic Nominals (2024)
    The paper models Modern Standard Arabic nouns, adjectives and elatives inside the CAMeL Morph framework (Habash et al., 2022), an open project that uses compatibility rules between allomorphs and an editable lexicon.
  9. Camel Morph MSA: A Large-Scale Open-Source Morphological Analyzer for Modern Standard Arabic (2024)
    The paper presents an open-source analyzer and generator for Modern Standard Arabic, built in the CAMeL Morph framework.
  10. CamelParser2.0: A State-of-the-Art Dependency Parser for Arabic (2023)
    An open-source Arabic parsing pipeline for both the CATiB and the UD formalisms. Raw text is normalised and stripped of diacritics, then a morphological disambiguator from CAMeL Tools (a BERT model or a lighter MLE one) gives tokens, lemmas, POS and features, including position-marked proclitics and enclitics and a…
  11. Camelira: An Arabic Multi-Dialect Morphological Disambiguator (2022)
    Camelira is a public web interface that disambiguates Arabic sentences in four varieties: MSA, Egyptian, Gulf and Levantine.
  12. Morphotactic Modeling in an Open-source Multi-dialectal Arabic Morphological Analyzer and Generator (2022)
    The paper describes CAMeL Morph, an open framework for writing Arabic morphology as specifications and compiling them into a database that the Camel Tools analyser and generator can use.
  13. Camel Treebank: An Open Multi-genre Arabic Dependency Treebank (2022)
    Camel Treebank 1.0 is an open dependency treebank of about 188k words (about 242k tokens) of Modern Standard and Classical Arabic, in the Columbia Arabic Treebank (CATiB) style.
  14. Joint Diacritization, Lemmatization, Normalization, and Fine-Grained Morphological Tagging (2020)
    Arabic lemmas and diacritized forms are open-vocabulary and best modelled on characters, while POS and the fourteen closed features are word-level tags.
  15. Morphological Analysis and Disambiguation for Gulf Arabic: The Interplay between Resources and Methods (2020)
    This is the first full morphological analysis and disambiguation system for Gulf Arabic (Emirati data). The analyser for Gulf Arabic is not written by hand: it is built by paradigm completion from the training split of the Annotated Gumar Corpus (about 202,000 tokens, eight novel excerpts). Two hand-built analysers…
  16. Adversarial Multitask Learning for Joint Multi-Feature and Multi-Dialect Morphological Modeling (2019)
    The authors tag fourteen Arabic morphological features (POS, aspect, case, gender, and others) with one Bi-LSTM whose hidden layers are shared across features, instead of one model per feature.
  17. Morphologically Annotated Corpora for Seven Arabic Dialects: Taizi, Sanaani, Najdi, Jordanian, Syrian, Iraqi and Moroccan (2019)
    The paper releases seven small manually annotated corpora of Arabic dialects (Taizi and Sanaani Yemeni, Najdi, Jordanian, Syrian Damascene, Iraqi Baghdadi, Moroccan Rabati), together over 200,000 words, each about 20,000 to 35,000 words.
  18. An Arabic Dependency Treebank in the Travel Domain (2019)
    The authors build a small dependency treebank of Modern Standard Arabic from the travel-phrase corpus BTEC, in the Columbia Arabic Treebank (CATiB) style, so that it can be compared with the news-based Penn Arabic Treebank.
  19. An Arabic Morphological Analyzer and Generator with Copious Features (2018)
    The paper presents CALIMA Star, an Arabic analyzer and generator built on the BAMA/SAMA/ALMOR family of pre-compiled six-table databases (three lexicon tables for prefixes, stems and suffixes, three compatibility tables).
  20. Noise-Robust Morphological Disambiguation for Dialectal Arabic (2018)
    The paper builds a morphological disambiguator for Egyptian Arabic, where spelling is unstandardised and most words have many analyses (about 24 per word, against about 12 in MSA).
  21. CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies (2017)
    The shared task asks systems to parse raw text, with no gold tokenization, sentence splitting or tags, into UD trees for 49 languages.
  22. Don't Throw Those Morphological Analyzers Away Just Yet: Neural Morphological Disambiguation for Arabic (2017)
    A morphological analyzer gives several readings for each Arabic word when taken out of context, and the task is to choose the right one in context.
  23. Universal Dependencies for Arabic (2017)
    The paper presents NUDAR, a Universal Dependencies treebank for Modern Standard Arabic of 738,889 tokens in 19,738 sentences, made by converting the Penn Arabic Treebank (parts 1–3).
  24. Exploiting Arabic Diacritization for High Quality Automatic Annotation (2016) 1 idea kept
    Undiacritized Arabic is highly ambiguous: about 12.8 analyses per word out of context. The authors use the diacritics that a text does have to choose among those analyses. MADAMIRA (with the SAMA analyzer) ranks the candidates as usual; then the candidates are filtered by the edit distance between their diacritized…
  25. CamelParser: A system for Arabic Syntactic Analysis and Morphological Disambiguation (2016)
    CamelParser is a public system that builds Arabic dependency trees (in the CATiB style) with the same morphological features that MADAMIRA produces, and then uses the syntax to correct MADAMIRA's choice of case and state.
  26. Improving Arabic Diacritization through Syntactic Analysis (2015)
    MADAMIRA chooses a morphological analysis from a ranked list for each word, but it looks only at a small window of neighbouring words and has no syntax.
  27. MADAMIRA: A Fast, Comprehensive Tool for Morphological Analysis and Disambiguation of Arabic (2014)
    MADAMIRA merges two older Arabic tools, MADA (morphology and disambiguation) and AMIRA (tokenization, tagging, chunking), into one Java system.
  28. Dependency Parsing of Modern Standard Arabic with Lexical and Inflectional Features (2013)
    The paper asks which morphological features help dependency parsing of MSA, using CATiB trees and two transition-based parsers (MaltParser and Easy-First).
  29. Identifying Broken Plurals, Irregular Gender, and Rationality in Arabic Text (2012)
    Arabic words can carry a mismatch between form and function: a broken plural looks singular, and some nouns have a feminine form with masculine agreement, or the reverse.
  30. A Morphological Analyzer for Egyptian Arabic (2012)
    The paper presents CALIMA, a morphological analyzer for Egyptian Arabic (EGY), built by extending an older lexicon, the Egyptian Colloquial Arabic Lexicon (ECAL, about 66K entries).
  31. Hebrew Morphological Preprocessing for Statistical Machine Translation (2012)
    The authors compare ways of splitting Hebrew words into tokens before Hebrew-to-English statistical translation with Moses, on a training set of about 64,000 sentences.
  32. A Corpus for Modeling Morpho-Syntactic Agreement in Arabic: Gender, Number and Rationality (2011)
    The authors add manually annotated functional features to the nominals of PATB part 3: gender, number and rationality (human or not), as opposed to the form-based features the affixes show.
  33. Improving Arabic Dependency Parsing with Form-based and Functional Morphological Features (2011)
    The authors ask which morphological features help a transition-based parser (MaltParser, eager algorithm, SVM classifiers) on Modern Standard Arabic.
  34. Morphological Annotation of Quranic Arabic (2010)
    The paper describes how the Quranic Arabic Corpus got its morphological layer: segmentation of each word into stem and affixes, with a part-of-speech tag and inflectional features per segment, following the traditional Arabic grammar tradition.
  35. Improving Arabic Dependency Parsing with Lexical and Inflectional Morphological Features (2010)
    Marton, Habash and Rambow test which morphological and lexical features help a transition-based parser (MaltParser) on the Columbia Arabic Treebank (CATiB, converted from PATB part 3, gold segmentation).
  36. Morphological Analysis and Generation of Arabic Nouns: A Morphemic Functional Approach (2010)
    MAGEAD is a morphological analyser and generator for Arabic built as finite-state transducers. It maps a lexeme and feature-value pairs to a surface form and back. This paper ports it from verbs to Modern Standard Arabic nominals, which are harder because of broken plurals and irregular feminines. A lexeme is a root…
  37. Machine Translation between Hebrew and Arabic: Needs, Challenges and Preliminary Solutions (2010)
    Modern Hebrew and Standard Arabic share orthography, root-and-pattern morphology, clitics and much of their vocabulary, but they differ in case, dual number, broken plurals, the feminine ending in genitive constructions and the agreement of irrational plural nouns.
  38. CATiB: The Columbia Arabic Treebank (2009)
    CATiB is an Arabic dependency treebank built for speed, for training parsers. It uses 6 part-of-speech tags (against more than 400 in the Penn Arabic Treebank) and 8 dependency labels, with terms from the traditional Arabic grammar (idafa, tamyiz). Case is left out, because it follows from syntax, and empty…
  39. Arabic Morphological Tagging, Diacritization, and Lemmatization Using Lexeme Models and Feature Ranking (2008)
    MADA picks, for each Arabic word, one analysis from the candidates that the BAMA dictionary proposes. It scores each candidate by summing the weights of the features on which the candidate agrees with the model's prediction. The features are 14 morphological tags, each predicted by an SVM, two checks (spelling match…
  40. Arabic Diacritization through Full Morphological Tagging (2007)
    The authors restore diacritics by choosing a whole diacritized analysis for each white-space token, not by labelling characters.
  41. Semi-automatic error analysis for large-scale statistical machine translation (2007)
    The paper relates properties of the input documents to the translation quality of a large SMT system, scored per document by HTER.
  42. MAGEAD: A Morphological Analyzer and Generator for the Arabic Dialects (2006)
    MAGEAD is a finite-state morphological analyzer and generator for MSA and for Levantine verbs. A lexeme is a root, a meaning index and a morphological behaviour class; patterns and vocalisms are interdigitated with the root on a multitape machine (Kiraz's approach, with an added tier for orthography), and affixes are…
  43. Parsing Arabic Dialects (2006)
    Levantine Arabic (LA) is spoken, unwritten, and has almost no treebank, while MSA has the Penn Arabic Treebank (about 17,600 training sentences).
  44. Arabic Tokenization, Part-of-Speech Tagging and Morphological Disambiguation in One Fell Swoop (2005)
    Tokenization, POS tagging and morphological disambiguation are handled as one step for undiacritized Arabic.
  45. Morphological Analysis and Generation for Arabic Dialects (2005)
    The paper presents MAGEAD, a finite-state morphological analyzer and generator for Modern Standard Arabic and its dialects.
  46. CatVar: A Database of Categorial Variations for English (2003)
    CatVar is a database of categorial variations of English lexemes: a noun, a verb and an adjective that share one root, such as "destroy", "destruction" and "destructive".
  47. Generation-Heavy Hybrid Machine Translation (2002)
    The paper proposes a way to translate between structurally divergent languages when only the target language is rich in resources.
  48. Generation from Lexical Conceptual Structures (2000)
    The paper describes a generator that turns Lexical Conceptual Structures (LCS), a compositional, language-independent interlingua, into English sentences.

Co-authors (117)

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/authors/nizar-habash/