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 Japanese UPOS tagging now.
| Group | Tag | Meaning | Example |
|---|---|---|---|
| Open Class | ADJ | Adjective | 大きい, 古い, 緑の, 理解不能な, 最初の |
| ADV | Adverb | とても, 明日, 下へ, どこ, そこ | |
| INTJ | Interjection | しーっ, 痛い, ブラボー, こんにちは | |
| NOUN | Noun (common) | 女の子, 猫, 木, 空気, 美しさ | |
| PROPN | Proper Noun | メアリー, ジョン, ロンドン, NATO, HBO | |
| VERB | Verb | 走る, 走る, 走っている, 食べる, 食べた, 食べられた | |
| Closed Class | ADP | Adposition | で, に, の間 |
| AUX | Auxiliary | だ, 〜した, 〜する, 〜すべき | |
| CONJ | Conjunction | と, または, しかし（古いタグ） | |
| CCONJ | Coordinating Conjunction | と, または, しかし | |
| SCONJ | Subordinating Conjunction | 〜なら, 〜の間, 〜と | |
| DET | Determiner | —, —, — | |
| NUM | Numeral | 1, 2017, 一, 七十七, MMXIV | |
| PART | Particle | の, ない | |
| PRON | Pronoun | 私, あなた, 彼, 彼女, 自分自身, 彼ら自身, 誰か | |
| 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.
Japanese XPOS tags in spaCy (primarily using the UniDic or IPADIC dictionaries) are hierarchical, with levels separated by hyphens (e.g., 名詞-普通名詞-一般). Unlike English, which uses short alphanumeric codes, Japanese tags are descriptive Kanji strings that define the part of speech (POS) across up to four levels of granularity. This hierarchy allows for precise distinction between types of nouns (like common nouns vs. proper nouns) and the specific functional roles of particles (Josa), which are essential for determining the grammatical relationships in a Japanese sentence.
Try our Japanese XPOS tagging now.
| Category | Abbreviation (Hierarchy) | Japanese Term | English Meaning | Example |
|---|---|---|---|---|
| Nouns (名詞) | 名詞-普通名詞-一般 | 普通名詞 | Common Noun | 本 (book), 猫 (cat) |
| 名詞-普通名詞-サ変可能 | サ変名詞 | Suru-Verb Noun (Potential) | 勉強 (study), 散歩 (walk) | |
| 名詞-普通名詞-副詞可能 | 副詞可能名詞 | Adverbial Noun | 今日 (today), 一番 | |
| 名詞-固有名詞-一般 | 固有名詞 | Proper Noun | カップヌードル、奥の細道 | |
| 名詞-固有名詞-人名 | 人名 | Person Name | 田中, 太郎 | |
| 名詞-固有名詞-地名 | 地名 | Place Name | 日本, 東京 | |
| 名詞-数詞 | 数詞 | Numeral | 一, 三, 100 | |
| Verbs (動詞) | 動詞-一般 | 一般動詞 | General Verb | 行く (go), 食べる (eat) |
| 動詞-非自立可能 | 非自立動詞 | Dependent/Auxiliary Verb | 〜ている, 〜てみる | |
| 助動詞 | 助動詞 | Auxiliary Verb | 〜です, 〜ます, 〜ない | |
| Adjectives | 形容詞-一般 | い形容詞 | Adjective (I-adj) | 美味しい, 高い |
| 形状詞-一般 | な形容詞 | Adjectival Noun (Na-adj stem) | 綺麗, 静か | |
| Particles (助詞) | 助詞-格助詞 | 格助詞 | Case Particle | が, を, に, へ, と |
| 助詞-係助詞 | 係助詞 | Binding Particle | は, も, こそ | |
| 助詞-副助詞 | 副助詞 | Adverbial Particle | だけ, ばかり, くらい | |
| 助詞-接続助詞 | 接続助詞 | Conjunctive Particle | から, ので, て, ば | |
| 助詞-終助詞 | 終助詞 | Sentence-final Particle | ね, よ, か | |
| Other Categories | 代名詞 | 代名詞 | Pronoun | これ, 私, あなた |
| 副詞 | 副詞 | Adverb | すぐ, ゆっくり, 非常に | |
| 連体詞 | 連体詞 | Adnominal (Determiner) | この, あの, 大きな | |
| 接続詞 | 接続詞 | Conjunction | そして, しかし, だから | |
| 感動詞 | 感動詞 | Interjection | はい, ああ, もしもし | |
| 接頭辞 | 接頭辞 | Prefix | お名前 | |
| 接尾辞 | 接尾辞 | Suffix | 食べさせる | |
| 補助記号-句点 | 句点 | Period Punctuation | 。 | |
| 補助記号-読点 | 読点 | Supplemental Punctuation | 、 |
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 | イーロンが食べる。 |
| csubj | Clausal subject | 彼がしたことは間違っていた。 | |
| obj | Direct object | 私は月を見る。 | |
| iobj | Indirect object | 彼女は私にプレゼントをくれた。 | |
| ccomp | Clausal complement (finite) | 彼は疲れたと言った。 | |
| xcomp | Open clausal complement | 私は行きたい。 | |
| Non-Core Dependents | obl | Oblique nominal | 彼は椅子に座った。 |
| vocative | Vocative | ジョン、ここに来なさい！ | |
| expl | Expletive | あそこに猫がいる。 | |
| dislocated | Dislocated element | あの男を私は知っている。 | |
| advcl | Adverbial clause modifier | 彼が到着した後に私は出発した。 | |
| advmod | Adverbial modifier | 速く走れ。 | |
| discourse | Discourse element | まあ、よく分かりません。 | |
| aux | Auxiliary | 私は見ることができる。 | |
| cop | Copula | 彼女は幸せだ。 | |
| mark | Subordinating marker | あなたが知っていることを私は知っている。 | |
| Nominal Dependents | nmod | Nominal modifier | 車のドア。 |
| appos | Appositional modifier | サム、私の友人。 | |
| nummod | Numeric modifier | 7日間。 | |
| acl | Adjectival clause | 勝つための計画。 | |
| amod | Adjectival modifier | 青い空。 | |
| det | Determiner | 終わり。 | |
| case | Case marking | フランスの王。 | |
| fixed | Fixed multiword expression | それにもかかわらず。 | |
| flat | Flat multiword name | ニューヨーク市。 | |
| compound | Compound noun | 電話ボックス。 | |
| list | List element | 電話、鍵、財布。 | |
| Coordination | conj | Conjunct | パンとバター。 |
| cc | Coordinating conjunction | パンとバター。 | |
| Special Labels | aux:pass | Passive auxiliary | それは盗まれた。 |
| punct | Punctuation | こんにちは！ | |
| dep | Unspecified dependency | （不明なリンクに使用） | |
| ROOT | Root of the sentence | 昼食を食べた。 |
| Attachment | Full Name | Explanation | Example |
|---|---|---|---|
| :pass | Passive | Indicates a relationship in a passive voice construction. | nsubj:pass (窓が壊された) |
| :nn | Noun Compound | Indicates that a noun is modifying another noun in a compound structure. | compound:nn (電話の充電器) |
| :prep | Prepositional | Refines a modifier governed specifically by a preposition. | nmod:prep (マットの上の猫) |
| :assmod | Associative Modifier | Common in Romanian/Baltic languages; shows nouns modifying other nouns. | nmod:assmod (私の父の車) |
| :poss | Possessive | Indicates ownership or a possessive relationship. | nmod:poss (私の犬、ジョンの帽子) |
| :relcl | Relative Clause | Identifies a clause that modifies a noun phrase. | acl:relcl (私が読んだ本) |
| :tmod | Temporal Modifier | A modifier specifically describing time or duration. | nmod:tmod (火曜日に出発する) |
| :prt | Particle | Used for phrasal verb particles. | compound:prt (あきらめる、終了する) |
| :rcomp | Relative Complement | Used for complements of relative clauses (common in Dutch). | advcl:rcomp (立ち去った男) |
| :flat | Flat Modifier | Used for multi-word expressions that don't have a clear internal head. | flat:name (オバマ大統領) |
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) | 日本, 東京, フランス, カリフォルニア |
| 🏔️ LOC | Non-political location (mountains, rivers) | 太平洋, エベレスト, アルプス山脈 |
| 🏢 FAC | Facility (buildings, airports, highways) | ゴールデンゲートブリッジ, 成田国際空港, ブルジュ・ハリファ |
| 👤 PERSON | People (real or fictional) | イーロン・マスク, ハリー・ポッター, アラン・チューリング |
| 🚩 NORP | Nationalities, religious or political groups | アメリカ人, 仏教徒, 民主党員, 日本人 |
| 🏢 ORG | Organizations (companies, institutions) | Google, 国際連合, Apple, FIFA |
| 📅 DATE | Absolute or relative dates | 2026年7月4日, 昨日, 来週 |
| ⌚ TIME | Times smaller than a day | 午前9:30, 日の入り, 10分 |
| 🎊 EVENT | Named events (wars, festivals) | 第二次世界大戦, コーチェラ, オリンピック |
| 💰 MONEY | Monetary values, including unit | 100ドル, 500万ユーロ, 50ポンド |
| ‱ PERCENT | Percentage, including "%" | 20%, 80パーセント, 0.5% |
| ⚖️ QUANTITY | Measurements (weight, distance) | 5km, 50kg, 30平方メートル |
| 🔢 ORDINAL | "First", "second", etc. | 最初, 2番目, 9番目 |
| 🔢 CARDINAL | Numbers not classified elsewhere | 10, 1000, 3 |
| 📦 PRODUCT | Objects, vehicles, foods, etc. (not services) | iPhone, テスラ モデルS, コカ・コーラ |
| 🎨 WORK_OF_ART | Titles of books, songs, etc. | モナ・リザ, ボヘミアン・ラプソディ, ハムレット |
| 📜 LAW | Named legal documents | 憲法, ヴェルサイユ条約 |
| 🗣️ LANGUAGE | Named languages | 日本語, Python, 中国語 |
「Googleはカリフォルニア州に拠点を置いています」(Google is based in California)というフレーズを処理すると、分析レイヤーは次のようになります。
原形 (Lemma): "Google", "は", "カリフォルニア州", "に", "拠点", "を", "置く", "て", "いる", "ます"
UPOS: "PROPN(固有名詞)", "ADP(助詞)", "PROPN(固有名詞)", "ADP(助詞)", "NOUN(名詞)", "ADP(助詞)", "VERB(動詞)", "SCONJ(接続助詞)", "VERB(非自立動詞)", "AUX(助動詞)"
XPOS (UniDic): "名詞-固有名詞-地名-国", "助詞-係助詞", "名詞-固有名詞-地名-国", "助詞-格助詞", "名詞-普通名詞-一般", "助詞-格助詞", "動詞-一般", "助詞-接続助詞", "動詞-非自立可能", "助動詞"
DEP: 「Google」は係助詞「は」を伴って主題 (nsubj) となり、動詞「置い」がこの文のルート (Root) となります。「カリフォルニア州」は格助詞「に」を伴って場所を表す補語 (obl) となり、「拠点」は格助詞「を」を伴って目的語 (obj) となります。「て」は接続助詞、「い」は非自立動詞で補助動詞 (cop / aux) として機能します。
NER: 「Google」は 🏢 ORG (組織)、「カリフォルニア州」は 🌍 GPE (地政学的実体) です。
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
|
|||||