Universal POS, Detailed POS, NER, DEP

UPOS (Universal POS)

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 Hindi UPOS tagging now.

UPOS Universal Part-of-Speech
Group Tag Meaning Example
Open Class ADJ Adjective बड़ा, पुराना, हरा, समझ से बाहर, पहला
ADV Adverb बहुत, कल, नीचे, कहाँ, वहाँ
INTJ Interjection श्श्, आह, शाबाश, नमस्ते
NOUN Noun (common) लड़की, बिल्ली, पेड़, हवा, सुंदरता
PROPN Proper Noun मैरी, जॉन, लंदन, नाटो, एचबीओ
VERB Verb दौड़ना, दौड़ता है, दौड़ते हुए, खाना, खाया, खाया हुआ
Closed Class ADP Adposition में, को, के दौरान
AUX Auxiliary है, कर चुका है, करेगा, करना चाहिए
CONJ Conjunction और, या, लेकिन (विरासत टैग)
CCONJ Coordinating Conjunction और, या, लेकिन
SCONJ Subordinating Conjunction यदि, जबकि, कि
DET Determiner एक, —, —
NUM Numeral 1, 2017, एक, सतहत्तर, MMXIV
PART Particle का/की/के, नहीं
PRON Pronoun मैं, आप, वह, वह, मैं खुद, वे खुद, कोई
Other PUNCT Punctuation ., (, ), ?, ]
SYM Symbol $, %, +, −, :), 🐻
X Other / Foreign sfpksdpsxmsa, ..., foreign words
SPACE Space newlines, tabs, extra spaces

XPOS (Detailed POS)

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.

The Hindi XPOS tags follow the BIS (Bureau of Indian Standards) or IIIT-Hyderabad tagset. This system is designed to handle Hindi's SOV (Subject-Object-Verb) structure and its use of postpositions (grammatical markers that follow the noun).
One key distinction in this set is the separation of Main Verbs (VM) from Auxiliary Verbs (VAUX) and the specific tagging of Proper Noun Compounds (NNPC), which is crucial for accurate Named Entity Recognition.
The system emphasizes the distinction between main and auxiliary verbs and highlights the vital role of postpositions (PSP) which govern case relationships in Indo-Aryan languages.

Try our Hindi XPOS tagging now.

Hindi xpos tags
Category Tag Meaning Example
Nouns NN Common Noun किताब (book), शहर (city)
NNP Proper Noun दिल्ली (Delhi), भारत (India)
NNPC Proper Noun Compound (Part of name) महात्मा गांधी (The 'Mahatma' part)
Pronouns PRP Personal Pronoun मैं (I), हम (we), आप (you)
DEM Demonstrative Pronoun यह (this), वह (that)
Verbs VM Main Verb खा (eat), चल (walk), देख (see)
VAUX Auxiliary Verb है (is), था (was), रहा (continuing)
Adjectives JJ Adjective बड़ा (big), नीला (blue), अच्छा (good)
Adverbs RB Adverb तेज़ (fast), धीरे (slowly), अक्सर (often)
Postposition PSP Postposition (Case Marker) ने (ergative), को (to), में (in), से (from)
Quantifiers QC Cardinal Numeral एक (one), दो (two), दस (ten)
QO Ordinal Numeral पहला (first), दूसरा (second)
QF General Quantifier बहुत (much), कम (less), थोड़ा (little)
Particles RP Particle (Emphasis) भी (also), ही (only), तो (so)
NEG Negative Particle नहीं (not), न (no), मत (do not)
Others CC Conjunction और (and), या (or), लेकिन (but)
WQ Wh-word (Interrogative) क्या (what), क्यों (why), कहाँ (where)
NST Noun Spatio-Temporal (Locative) ऊपर (above), नीचे (below), पास (near)
SYM Symbol / Punctuation ।, ,, ?, !
INJ Interjection अरे (hey), वाह (wow)

Dependency

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.

DEP Full Syntactic Dependency Labels
Category Label Meaning Example (Token in bold)
Core Arguments nsubj Nominal subject एलोन खाता है।
csubj Clausal subject उसने जो किया वह गलत था।
obj Direct object मैं चाँद देखता हूँ।
iobj Indirect object उसने मुझे एक उपहार दिया।
ccomp Clausal complement (finite) उसने कहा कि वह थका हुआ था
xcomp Open clausal complement मैं जाना चाहता हूँ।
Non-Core Dependents obl Oblique nominal वह कुर्सी पर बैठा।
vocative Vocative जॉन, यहाँ आओ!
expl Expletive वहाँ एक बिल्ली है।
dislocated Dislocated element उस आदमी को मैं जानता हूँ।
advcl Adverbial clause modifier उसके आने के बाद मैं चला गया
advmod Adverbial modifier तेज़ दौड़ो।
discourse Discourse element खैर, मुझे यकीन नहीं है।
aux Auxiliary मैं देख सकता हूँ।
cop Copula वह खुश है
mark Subordinating marker मुझे पता है कि तुम जानते हो।
Nominal Dependents nmod Nominal modifier गाड़ी का दरवाज़ा।
appos Appositional modifier सैम, मेरा दोस्त
nummod Numeric modifier सात दिन।
acl Adjectival clause जीतने की योजना।
amod Adjectival modifier नीला आसमान।
det Determiner अंत।
case Case marking फ्रांस का राजा।
fixed Fixed multiword expression इसके बावजूद
flat Flat multiword name न्यूयॉर्क शहर।
compound Compound noun फ़ोन बूथ।
list List element फ़ोन, चाबियाँ, बटुआ
Coordination conj Conjunct रोटी और मक्खन
cc Coordinating conjunction रोटी और मक्खन।
Special Labels aux:pass Passive auxiliary यह चोरी हो गया
punct Punctuation नमस्ते!
dep Unspecified dependency (अज्ञान संबंधों के लिए उपयोग किया जाता है)
ROOT Root of the sentence मैंने दोपहर का भोजन किया

Common Dependency Attachments (Sub-labels)
Attachment Full Name Explanation Example
:pass Passive Indicates a relationship in a passive voice construction. nsubj:pass (खिड़की टूट गई थी)
:nn Noun Compound Indicates that a noun is modifying another noun in a compound structure. compound:nn (फ़ोन चार्जर)
:prep Prepositional Refines a modifier governed specifically by a preposition. nmod:prep (चटाई पर बिल्ली)
:assmod Associative Modifier Common in Romanian/Baltic languages; shows nouns modifying other nouns. nmod:assmod (मेरे पिता की गाड़ी)
:poss Possessive Indicates ownership or a possessive relationship. nmod:poss (मेरा कुत्ता, जॉन की टोपी)
:relcl Relative Clause Identifies a clause that modifies a noun phrase. acl:relcl (वह पुस्तक जो मैंने पढ़ी)
:tmod Temporal Modifier A modifier specifically describing time or duration. nmod:tmod (मैं मंगलवार को जा रहा हूँ)
:prt Particle Used for phrasal verb particles. compound:prt (हार मानना, बंद करना)
:rcomp Relative Complement Used for complements of relative clauses (common in Dutch). advcl:rcomp (वह आदमी जो चला गया)
:flat Flat Modifier Used for multi-word expressions that don't have a clear internal head. flat:name (राष्ट्रपति ओबामा)

Named Entity Recognition

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.

NER Named Entity Recognition
Label Meaning Example
🌍 GPE Geopolitical entity (countries, cities, states) भारत, नई दिल्ली, फ्रांस, कैलिफ़ोर्निया
🏔️ LOC Non-political location (mountains, rivers) प्रशांत महासागर, माउंट एवरेस्ट, आल्प्स पर्वत
🏢 FAC Facility (buildings, airports, highways) गोल्डन गेट ब्रिज, जेएफके हवाई अड्डा, बुर्ज खलीफा
👤 PERSON People (real or fictional) एलोन मस्क, हैरी पॉटर, एलन ट्यूरिंग
🚩 NORP Nationalities, religious or political groups भारतीय, बौद्ध, डेमोक्रेट्स, जापानी
🏢 ORG Organizations (companies, institutions) गूगल, संयुक्त राष्ट्र, एप्पल, फीफा
📅 DATE Absolute or relative dates 4 जुलाई, 2026, कल, अगले सप्ताह
⌚ TIME Times smaller than a day सुबह 9:30 बजे, सूर्यास्त, दस मिनट
🎊 EVENT Named events (wars, festivals) द्वितीय विश्व युद्ध, कोचेला, ओलंपिक खेल
💰 MONEY Monetary values, including unit $100, 5 मिलियन यूरो, £50
‱ PERCENT Percentage, including "%" 20%, अस्सी प्रतिशत, 0.5%
⚖️ QUANTITY Measurements (weight, distance) 5 किमी, 50 किलोग्राम, 30 वर्ग मीटर
🔢 ORDINAL "First", "second", etc. पहला, दूसरा, नौवां
🔢 CARDINAL Numbers not classified elsewhere 10, एक हजार, तीन
📦 PRODUCT Objects, vehicles, foods, etc. (not services) आईफोन, टेस्ला मॉडल एस, कोका-कोला
🎨 WORK_OF_ART Titles of books, songs, etc. मोना लिसा, बोहेमियन रैप्सोडी, हैमलेट
📜 LAW Named legal documents संविधान, वर्साय की संधि
🗣️ LANGUAGE Named languages हिंदी, पायथन, मंदारिन

एनएलपी उदाहरण (NLP Example)

यदि हम वाक्य "गूगल कैलिफ़ोर्निया में स्थित है" (Google is based in California) को संसाधित करते हैं, तो विश्लेषण की परतें इस प्रकार दिखती हैं:

मूल शब्द (Lemma): "गूगल", "कैलिफ़ोर्निया", "में", "स्थित", "होना"
UPOS: "PROPN(व्यक्तिवाचक संज्ञा)", "PROPN(व्यक्तिवाचक संज्ञा)", "ADP(परसर्ग/संबोधक)", "ADJ(विशेषण)", "AUX(सहायक क्रिया)"
XPOS (BIS/IIIT): "NNP", "NNP", "PSP", "JJ", "VAUX"
DEP: "गूगल" संज्ञा कर्ता (nsubj) है, "स्थित" मुख्य शब्द (Root) है। "कैलिफ़ोर्निया" परसर्ग "में" के साथ क्रिया-विशेषण रूप (obl) से जुड़ा है। "है" सहायक क्रिया (aux) है।
NER: "गूगल" एक 🏢 ORG (संगठन) है, "कैलिफ़ोर्निया" एक 🌍 GPE (भू-राजनीतिक इकाई) है।

Part-of-Speech for Main Languages

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

  • Home
  • Translators
  • Dictionaries
  • Grammars
  • Keyboards
  • Facebook

    © Stars21 - All Rights Reserved