--- title: "NUM: numeral — definition and key papers — Elamur Research" description: "NUM is the Universal Dependencies part-of-speech tag for numerals. Among them: Universal Dependencies v1: A Multilingual Treebank…" canonical: "https://research.elamur.ai/free/en/concepts/upos-num/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/concepts/upos-num/) [home](https://md.research.elamur.ai/free/en/) / [concepts](https://md.research.elamur.ai/free/en/concepts/) / NUM: numeral # 🏷️ NUM: numeral Universal Dependencies · 7 key papers · [all concepts](https://md.research.elamur.ai/free/en/concepts/) Part of: [🗨️ Natural language processing](https://md.research.elamur.ai/free/en/concepts/natural-language-processing/) · [🌐 Universal Dependencies](https://md.research.elamur.ai/free/en/concepts/universal-dependencies/) NUM is the Universal Dependencies part-of-speech tag for numerals. It covers words, digit strings and symbols that state a quantity or a number, typically cardinal numbers such as *three*, *17* or *XIV*. These usually modify a noun to say how many things there are. Also: numeral, cardinal number, Num (as a lexical category in descriptive grammar) ## What it is In [Universal Dependencies](https://md.research.elamur.ai/free/en/concepts/universal-dependencies/), NUM is one of seventeen universal part-of-speech tags. The inventory is closed: languages may refine relations with subtypes but may not add new basic tags ([Nivre et al. 2020](https://md.research.elamur.ai/free/en/papers/nivre-2020-universal-dependencies-v2-evergrowing-multilingual/)). In the guidelines' terms, a numeral expresses a number and answers the question "how many?". The tag is applied by function and form together. Cardinals written as words, as Arabic digits or as Roman numerals all receive NUM. The category is deliberately narrow. Several kinds of number words go elsewhere: - Ordinals such as *first* or *21st* behave like adjectives and are tagged ADJ. - Multiplicatives such as *twice* are ADV. - Quantifiers that name no exact number (*many*, *several*, *few*) are usually DET. - A numeral used as a noun phrase on its own, as in "*one* of them", may be tagged PRON in some treebanks, depending on language-specific practice. - Nouns of quantity such as *dozen* or *couple* are usually NOUN. The tag goes back to the compact universal tagset of Petrov, Das and McDonald (2012). NUM was one of its twelve coarse categories, defined pragmatically after the authors surveyed the guidelines of many existing corpora ([Petrov et al. 2012](https://md.research.elamur.ai/free/en/papers/petrov-2012-universal-part-speech-tagset/)). When UD v1 extended that set to seventeen tags, NUM was carried over unchanged ([Nivre et al. 2016](https://md.research.elamur.ai/free/en/papers/nivre-2016-universal-dependencies-v1-multilingual-treebank/)). ## Examples In English, a NUM word normally depends on the noun it counts through the `nummod` relation: - *She bought three apples* — *three* (NUM) is attached to *apples* by `nummod`. - *The 1990s* or *in 2019* — the year is NUM. In a prepositional phrase it heads its own nominal and is attached as `obl` or `nmod`. - *two or three days* — *three* is a `conj` of *two*. - *Chapter 4* — the digit modifies or follows the noun, and its attachment varies by treebank. Typical morphological features (FEATS) for NUM words include: | Feature | Typical values | Example | | --- | --- | --- | | NumType | Card (also Frac, Range in some treebanks) | *seven*, *½* | | NumForm | Word, Digit, Roman | *seven*, *7*, *VII* | | Number, Gender, Case | language-dependent | Russian *двух* (Case=Gen) | These features descend from the Interset approach of Zeman (2008). Interset is a universal inventory of morphosyntactic features that serves as an interlingua when converting between tagsets ([Zeman 2008](https://md.research.elamur.ai/free/en/papers/zeman-2008-reusable-tagset-conversion-tagset-drivers/)). UD adopted such features as part of its morphological layer ([Nivre et al. 2016](https://md.research.elamur.ai/free/en/papers/nivre-2016-universal-dependencies-v1-multilingual-treebank/)). ## Across languages Numerals are a classic area of cross-linguistic variation, and UD handles it mostly through relations and features rather than through new tags. - Slavic languages: from "five" upward, Russian and Czech numerals govern the genitive plural of the noun, as in *пять книг* 'five books'. UD marks this with the subtype `nummod:gov`, while agreeing numerals take plain `nummod`. - Chinese and Japanese: a classifier stands between the numeral and the noun. In Chinese 三本书 'three books', 三 is NUM and the classifier 本 is linked by `clf`. - French and other Romance languages: complex numerals such as *vingt et un* 'twenty-one' or *deux mille* 'two thousand' are split into several tokens. These are joined by `flat` or `compound` relations. - Arabic and Hebrew: cardinals show gender polarity, so the numeral's gender is the opposite of the counted noun's. - Spaces inside numbers: UD v2 allows a space inside a word only for numbers and abbreviations in languages that otherwise separate words with spaces. A form like French *10,000* can therefore remain a single NUM token ([Nivre et al. 2020](https://md.research.elamur.ai/free/en/papers/nivre-2020-universal-dependencies-v2-evergrowing-multilingual/)). These choices follow UD's general design. Content words head the tree, and the relation label signals what kind of dependent each word is ([Marneffe et al. 2021](https://md.research.elamur.ai/free/en/papers/marneffe-2021-universal-dependencies/)). ## In treebanks and research In both English and French treebanks, NUM accounts for well under two percent of tokens. `nummod` is by far its dominant relation. The next most frequent relations are `nmod` and `obl`, which cover dates, years, quantities and numbered references that head their own phrases. English shows NUM unusually often as `root` and `conj`, reflecting headings, list items and ranges. French makes more frequent use of `flat` for multiword numerals. The tag matters for several kinds of work: - [Part-of-speech tagging](https://md.research.elamur.ai/free/en/concepts/part-of-speech-tagging/): digit strings make NUM easy to recognise at the surface. Spelled-out numerals and borderline words such as *one* remain a source of disagreement. - Cross-lingual transfer: Petrov et al. showed that coarse tags such as NUM support direct transfer of delexicalised parsers across languages ([Petrov et al. 2012](https://md.research.elamur.ai/free/en/papers/petrov-2012-universal-part-speech-tagset/)). - Annotation consistency: inconsistencies in the tagging of numerals and quantifiers are among the issues that UD consistency checks aim to detect ([Marneffe et al. 2017](https://md.research.elamur.ai/free/en/papers/marneffe-2017-assessing-annotation-consistency-universal-dependencies/)). Treebanks of the same language can also be compared through the divergence of their UPOS trigram distributions ([Aggarwal & Zeman 2020](https://md.research.elamur.ai/free/en/papers/aggarwal-2020-estimating-pos-annotation-consistency-different/)). - Downstream tasks: numerals in a [dependency parsing](https://md.research.elamur.ai/free/en/concepts/dependency-parsing/) output give [information extraction](https://md.research.elamur.ai/free/en/concepts/information-extraction/) and [named entity recognition](https://md.research.elamur.ai/free/en/concepts/named-entity-recognition/) systems a direct route to quantities, dates and amounts. How often the tag NUM occurs: its share of all tokens Counted by code over the Universal Dependencies 2.18 treebanks of English and French (every token once, subtypes with their base relation). **The numbers** | Treebanks | Share | | --- | --- | | English treebanks | 1.47% of tokens (16,548 tokens) | | French treebanks | 1.54% of tokens (16,787 tokens) | The relations NUM words take most often The five most frequent in each language's treebanks, by tokens. **The numbers** | Pair | Tokens | | --- | --- | | English: nummod | 6,711 | | English: nmod | 1,668 | | English: obl | 1,317 | | English: root | 1,042 | | English: conj | 1,036 | | French: nummod | 7,191 | | French: nmod | 4,036 | | French: obl | 3,459 | | French: conj | 642 | | French: flat | 535 | ## Key papers The works this page cites, the most cited first; citations as counted by OpenAlex plus the papers of this library that cite the work, read 2026-10-24. - [Universal Dependencies v1: A Multilingual Treebank Collection](https://md.research.elamur.ai/free/en/papers/nivre-2016-universal-dependencies-v1-multilingual-treebank/) — Joakim Nivre, Marie-Catherine de Marneffe, Filip Ginter et al. · 2016 · 1,741 citations - [A Universal Part-of-Speech Tagset](https://md.research.elamur.ai/free/en/papers/petrov-2012-universal-part-speech-tagset/) — Slav Petrov, Dipanjan Das, Ryan McDonald · 2012 · 1,180 citations - [Universal Dependencies](https://md.research.elamur.ai/free/en/papers/marneffe-2021-universal-dependencies/) — Marie-Catherine de Marneffe, Christopher D. Manning, Joakim Nivre et al. · 2021 · 480 citations - [Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection](https://md.research.elamur.ai/free/en/papers/nivre-2020-universal-dependencies-v2-evergrowing-multilingual/) — Joakim Nivre, Marie-Catherine de Marneffe, Filip Ginter et al. · 2020 · 325 citations - [Reusable Tagset Conversion Using Tagset Drivers](https://md.research.elamur.ai/free/en/papers/zeman-2008-reusable-tagset-conversion-tagset-drivers/) — Daniel Zeman · 2008 · 181 citations - [Assessing the Annotation Consistency of the Universal Dependencies Corpora](https://md.research.elamur.ai/free/en/papers/marneffe-2017-assessing-annotation-consistency-universal-dependencies/) — Marie-Catherine de Marneffe, Matias Grioni, Jenna Kanerva et al. · 2017 · 30 citations - [Estimating POS Annotation Consistency of Different Treebanks in a Language](https://md.research.elamur.ai/free/en/papers/aggarwal-2020-estimating-pos-annotation-consistency-different/) — Akshay Aggarwal, Daniel Zeman · 2020 · 7 citations ## Related concepts - [Universal Dependencies](https://md.research.elamur.ai/free/en/concepts/universal-dependencies/) — Universal Dependencies is a framework and an open collection of treebanks that annotates the grammar of many languages with one shared… - [Part-of-speech tagging](https://md.research.elamur.ai/free/en/concepts/part-of-speech-tagging/) — Part-of-speech tagging is the task of assigning each token in a text a grammatical category, such as noun, verb, adjective or determiner… - [Morphology](https://md.research.elamur.ai/free/en/concepts/morphology/) — Morphology is the branch of linguistics that studies the internal structure of words. It covers how words are built from meaningful units… ## More papers Topics: [🔤 Part-of-speech tagging](https://md.research.elamur.ai/free/en/topics/part-of-speech-tagging/) · [🌐 Universal Dependencies](https://md.research.elamur.ai/free/en/topics/universal-dependencies/) Shelves: [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) - [← previous concept nsubj: nominal subject](https://md.research.elamur.ai/free/en/concepts/ud-nsubj/) - [next concept → nummod: numeric modifier](https://md.research.elamur.ai/free/en/concepts/ud-nummod/) - [↑ back to concepts](https://md.research.elamur.ai/free/en/concepts/)