UPOS (Universal Part-of-Speech) tags are a core component of the Universal Dependencies (UD) project, designed to provide a standardized, fixed set of 17 categories that remain consistent across all human languages. Unlike language-specific systems (XPOS), which reflect the unique morphological intricacies of a single tongue, UPOS focuses on the functional role of a word. By stripping away language-specific "noise," UPOS allows researchers and developers to compare syntactic structures cross-linguistically and facilitates Cross-Lingual Transfer Learning—where an AI model trained on one language (like English) can apply its structural knowledge to another (like Romanian or Korean). It essentially serves as a "Lingua Franca" for computational linguistics, ensuring that a NOUN remains a NOUN whether the underlying grammar is agglutinative, fusional, or analytic.
Try our Arabic UPOS tagging now.
| Group | Tag | Meaning | Example |
|---|---|---|---|
| Open Class | ADJ | Adjective | كبير، قديم، أخضر، غير مفهوم، أول |
| ADV | Adverb | جداً، غداً، أسفل، أين، هناك | |
| INTJ | Interjection | صه، آخ، أحسنت، مرحباً | |
| NOUN | Noun (common) | بنت، قطة، شجرة، هواء، جمال | |
| PROPN | Proper Noun | مريم، جون، لندن، الناتو، إتش بي أو | |
| VERB | Verb | يجري، يركض، الجري، يأكل، أكل، مأكول | |
| Closed Class | ADP | Adposition | في، إلى، خلال |
| AUX | Auxiliary | يكون، فعل، سيفعل، يجب أن | |
| CONJ | Conjunction | و، أو، لكن (علامة قديمة) | |
| CCONJ | Coordinating Conjunction | و، أو، لكن | |
| SCONJ | Subordinating Conjunction | إذا، بينما، أن | |
| DET | Determiner | الـ (التعريف) | |
| NUM | Numeral | ١، ٢٠١٧، واحد، سبعة وسبعون، MMXIV | |
| PART | Particle | لا، ليس | |
| PRON | Pronoun | أنا، أنت، هو، هي، نفسي، أنفسهم، شخص ما | |
| Other | PUNCT | Punctuation | ., (, ), ?, ] |
| SYM | Symbol | $, %, +, −, :), 🐻 | |
| X | Other / Foreign | sfpksdpsxmsa, ..., foreign words | |
| SPACE | Space | newlines, tabs, extra spaces |
XPOS (Language-Specific Part-of-Speech) tagging offers a much higher level of granularity than the broader UPOS (Universal Part-of-Speech) system. While UPOS provides a standardized set of labels designed to work consistently across every language—ensuring that a NOUN in English is treated similarly to a NOUN in XPOS preserves the unique "linguistic DNA" of a specific language. It is the engine behind complex morphological analysis, allowing a system to distinguish not just that a word is a "Verb," but specifically that it is a "Third-Person, Singular, Past Tense, Passive Voice" verb. By capturing the deep grammatical details that UPOS omits for the sake of universality, XPOS enables the creation of translation tools and parsers that understand the precise inflectional logic of a specific culture and tongue.
Arabic XPOS tags follow the PADT (Prague Arabic Dependency Treebank) system.
They are positional strings exactly 10 characters long. Position 1 defines the primary Part of Speech (POS). For Verbs, the early positions (2-4) define Aspect, Mood, and Voice. For Nominals (Nouns and Adjectives), the later positions (7-10) define Gender, Number, Case, and State (Definiteness). This structure allows for incredibly precise mapping of Arabic's complex agglutinative morphology.
In N------S1D, positions 2 through 7 are empty because those features (Aspect, Mood, Voice, Person, Gender) are often redundant or fixed for that specific noun token.
In VP-A-3MS--, positions 9 and 10 are empty because Verbs do not have Case (Nominative/Genitive) or State (Definite/Indefinite) in Arabic grammar.
Try our Arabic XPOS tagging now.
| Group | Position | Category | Label | Meaning |
|---|---|---|---|---|
| Head Category (Pos 1) | 1 | Main POS | V | Verb (فعل) |
| 1 | Main POS | N | Noun (اسم) | |
| 1 | Main POS | A | Adjective (صفة) | |
| 1 | Main POS | S | Pronoun (ضمير) | |
| 1 | Main POS | P | Preposition (حرف جر) | |
| 1 | Main POS | C | Conjunction (حرف عطف) | |
| 1 | Main POS | M | Numeral (عدد) | |
| 1 | Main POS | Q | Particle (حرف) | |
| 1 | Main POS | I | Interjection (حرف نداء) | |
| 1 | Main POS | U | Punctuation / Symbol (علامة ترقيم) | |
| Verb Logic (Pos 2-4) | 2 | Aspect | P | Perfective (Past) |
| 2 | Aspect | I | Imperfective (Present/Future) | |
| 2 | Aspect | C | Imperative (Command) | |
| 3 | Mood | I | Indicative | |
| 3 | Mood | S | Subjunctive | |
| 3 | Mood | J | Jussive | |
| 4 | Voice | A / P | Active / Passive | |
| Inflection (Pos 6-8) | 6 | Person | 1, 2, 3 | 1st, 2nd, 3rd Person |
| 7 | Gender | M | Masculine (مذكر) | |
| 7 | Gender | F | Feminine (مؤنث) | |
| 8 | Number | S | Singular (مفرد) | |
| 8 | Number | D | Dual (مثنى) | |
| 8 | Number | P | Plural (جمع) | |
| Case & State (Pos 9-10) | 9 | Case | 1 | Nominative (مرفوع) |
| 9 | Case | 2 | Genitive (مجرور) | |
| 9 | Case | 4 | Accusative (منصوب) | |
| 10 | State | D | Definite (معرفة - Usually 'Al-') | |
| 10 | State | I | Indefinite (نكرة - Usually 'Tanween') | |
| 10 | State | C | Construct (مضاف - Idafa state) |
The DEP (Syntactic Dependency) refers to the specific grammatical relationship between a "child" token and its "head" (parent) token. While primary labels (like nsubj or obj) describe the basic structure, attachments starting with a colon (:) provide fine-grained sub-type information. For instance, while nsubj identifies a subject, :pass refines this to show the subject is being acted upon (Passive Voice). Similarly, :nn (Noun Compound) or :assmod (Associative Modifier) help the parser distinguish between simple modifiers and complex ownership or compound relationships, allowing for a much deeper "logical" understanding of the sentence.
| Category | Label | Meaning | Example (Token in bold) |
|---|---|---|---|
| Core Arguments | nsubj | Nominal subject | إيلون يأكل. |
| csubj | Clausal subject | ما فعله كان خاطئاً. | |
| obj | Direct object | أرى القمر. | |
| iobj | Indirect object | أعطتني هدية. | |
| ccomp | Clausal complement (finite) | قال إنه متعب. | |
| xcomp | Open clausal complement | أريد أن أذهب. | |
| Non-Core Dependents | obl | Oblique nominal | جلس على الكرسي. |
| vocative | Vocative | يا جون، تعال إلى هنا! | |
| expl | Expletive | هناك قطة. | |
| dislocated | Dislocated element | ذلك الرجل، أنا أعرفه. | |
| advcl | Adverbial clause modifier | رحلت بعد وصوله. | |
| advmod | Adverbial modifier | اركض بسرعة. | |
| discourse | Discourse element | حسناً، لست متأكداً. | |
| aux | Auxiliary | أستطيع أن أرى. | |
| cop | Copula | هي سعيدة. | |
| mark | Subordinating marker | أعلم أنك تعلم. | |
| Nominal Dependents | nmod | Nominal modifier | باب السيارة. |
| appos | Appositional modifier | سام، صديقي. | |
| nummod | Numeric modifier | سبعة أيام. | |
| acl | Adjectival clause | خطة الفوز. | |
| amod | Adjectival modifier | السماء الزرقاء. | |
| det | Determiner | الـنهاية. | |
| case | Case marking | ملك فرنسا. | |
| fixed | Fixed multiword expression | على الرغم من ذلك. | |
| flat | Flat multiword name | مدينة نيويورك. | |
| compound | Compound noun | كشك الهاتف. | |
| list | List element | الهاتف، المفاتيح، المحفظة. | |
| Coordination | conj | Conjunct | الخبز والزبدة. |
| cc | Coordinating conjunction | الخبز والزبدة. | |
| Special Labels | aux:pass | Passive auxiliary | لقد سُرِق. |
| punct | Punctuation | مرحباً! | |
| dep | Unspecified dependency | (تستخدم للروابط غير المعروفة) | |
| ROOT | Root of the sentence | تناولت الغداء. |
| Attachment | Full Name | Explanation | Example |
|---|---|---|---|
| :pass | Passive | Indicates a relationship in a passive voice construction. | nsubj:pass (كُسِر النافذة) |
| :nn | Noun Compound | Indicates that a noun is modifying another noun in a compound structure. | compound:nn (شاحن الهاتف) |
| :prep | Prepositional | Refines a modifier governed specifically by a preposition. | nmod:prep (القطة على السجادة) |
| :assmod | Associative Modifier | Common in Romanian/Baltic languages; shows nouns modifying other nouns. | nmod:assmod (سيارة أبي) |
| :poss | Possessive | Indicates ownership or a possessive relationship. | nmod:poss (كلبي، قبعة جون) |
| :relcl | Relative Clause | Identifies a clause that modifies a noun phrase. | acl:relcl (الكتاب الذي قرأته) |
| :tmod | Temporal Modifier | A modifier specifically describing time or duration. | nmod:tmod (سأغادر يوم الثلاثاء) |
| :prt | Particle | Used for phrasal verb particles. | compound:prt (استسلم، توقف) |
| :rcomp | Relative Complement | Used for complements of relative clauses (common in Dutch). | advcl:rcomp (الرجل الذي غادر) |
| :flat | Flat Modifier | Used for multi-word expressions that don't have a clear internal head. | flat:name (الرئيس أوباما) |
NER (Named Entity Recognition) is a Natural Language Processing (NLP) task that automatically identifies and categorizes key information (entities) in a text into predefined classes. In spaCy, the statistical model "looks" at the context of a word to determine if it refers to a person, an organization, a monetary value, or a specific date. This is crucial for extracting structured data from unstructured text, such as finding all the company names mentioned in a news article or identifying the dates of events in a history book.
Comparison Note: GPE vs. LOC
Determining whether a place is a GPE or a LOC depends on its political nature:
GPE (Geopolitical Entity): If the location has a government, specific laws, or human-defined administrative borders, it is labeled as a GPE. Examples include Seoul, Germany, the United Kingdom, and California.
LOC (Location): If the place is a natural physical feature or a broad geographic region without a singular governing body, it is labeled as a LOC. Examples include the Alps, the Pacific Ocean, the Middle East, and Mount Everest.
| Label | Meaning | Example |
|---|---|---|
| 🌍 GPE | Geopolitical entity (countries, cities, states) | مصر، القاهرة، فرنسا، كاليفورنيا |
| 🏔️ LOC | Non-political location (mountains, rivers) | المحيط الهادئ، جبل إفرست، جبال الألب |
| 🏢 FAC | Facility (buildings, airports, highways) | جسر البوابة الذهبية، مطار القاهرة الدولي، برج خليفة |
| 👤 PERSON | People (real or fictional) | أحمد زويل، هاري بوتر، نجيب محفوظ |
| 🚩 NORP | Nationalities, religious or political groups | عربي، بوذي، الديمقراطيون، ياباني |
| 🏢 ORG | Organizations (companies, institutions) | جوجل، الأمم المتحدة، أبل، الفيفا |
| 📅 DATE | Absolute or relative dates | ٤ يوليو، ٢٠٢٦، أمس، الأسبوع المقبل |
| ⌚ TIME | Times smaller than a day | ٩:٣٠ صباحاً، غروب الشمس، عشر دقائق |
| 🎊 EVENT | Named events (wars, festivals) | الحرب العالمية الثانية، مهرجان الجونة، الألعاب الأولمبية |
| 💰 MONEY | Monetary values, including unit | ١٠٠ دولار، ٥ ملايين يورو، ٥٠ جنيه إسترليني |
| ‱ PERCENT | Percentage, including "%" | ٢٠٪، ثمانون بالمائة، ٠.٥٪ |
| ⚖️ QUANTITY | Measurements (weight, distance) | ٥ كم، ١٠٠ رطل، ٣٠ متراً مربعاً |
| 🔢 ORDINAL | "First", "second", etc. | أولاً، الثاني، التاسع |
| 🔢 CARDINAL | Numbers not classified elsewhere | ١٠، ألف، ثلاثة |
| 📦 PRODUCT | Objects, vehicles, foods, etc. (not services) | آيفون، تسلا موديل إس، كوكا كولا |
| 🎨 WORK_OF_ART | Titles of books, songs, etc. | الموناليزا، ملحمة الحرافيش، هاملت |
| 📜 LAW | Named legal documents | الدستور، معاهدة فرساي |
| 🗣️ LANGUAGE | Named languages | العربية، بايثون، الماندرين |
إذا قمنا بمعالجة الجملة "يقع مقر جوجل في كاليفورنيا" ، فإن المستويات تبدو كالتالي:
Lemma (الجذر/الليمية): "وقع"، "مقر"، "جوجل"، "في"، "كاليفورنيا"
UPOS (أقسام الكلام العامة): "VERB(فعل)"، "NOUN(اسم)"، "PROPN(اسم علم)"، "ADP(حرف جر)"، "PROPN(اسم علم)"
XPOS (أقسام الكلام التفصيلية): "VIIA----(فعل مضارع معلوم)"، "N---D---(اسم مرفوع معرف)"، "N---G---(اسم علم مجرور مضاف إليه)"، "F-------(حرف جر)"، "N---G---(اسم علم مجرور بفي)"
DEP (العلاقات النحوية): "يقع" هو الـ Root (عامل الجملة الرئيسي). "مقر" هو الـ nsubj (فاعل مرفوع). "جوجل" هو الـ nmod:poss (مضاف إليه مجرور). "كاليفورنيا" هو الـ obl (شبه جملة متعلق بيقع).
NER (تمييز الكيانات المسمى): "جوجل" هو 🏢 ORG (منظمة)، و"كاليفورنيا" هو 🌍 GPE (كيان جيوسياسي).
Arabic -
Catalan -
Chinese -
Classical Chinese -
Croatian -
Danish -
Dutch -
English -
Filipino -
Finnish -
French -
German -
Greek -
Hebrew -
Hindi -
Italian -
Indonesian -
Japanese -
Korean -
Latin -
Lithuanian -
Macedonian -
Norwegian -
Polish -
Portuguese -
Romanian -
Russian -
Slovenian -
Sanskrit -
Spanish -
Swedish -
Tamil -
Thai -
Ukrainian -
Vietnamese
|
|
|
© Stars21 - All Rights Reserved
|
|||||