package google.cloud.language.v1
Get desktop application:
View/edit binary Protocol Buffers messages
Provides text analysis operations such as sentiment analysis and entity recognition.
Analyzes the sentiment of the provided text.
message
language_service.proto:966The sentiment analysis request message.
optional document = 1
Input document.
EncodingType encoding_type = 2
The encoding type used by the API to calculate sentence offsets.
message
language_service.proto:975The sentiment analysis response message.
optional document_sentiment = 1
The overall sentiment of the input document.
string language = 2
The language of the text, which will be the same as the language specified in the request or, if not specified, the automatically-detected language. See [Document.language][google.cloud.language.v1.Document.language] field for more details.
repeated sentences = 3
The sentiment for all the sentences in the document.
Finds named entities (currently proper names and common nouns) in the text along with entity types, salience, mentions for each entity, and other properties.
message
language_service.proto:1009The entity analysis request message.
optional document = 1
Input document.
EncodingType encoding_type = 2
The encoding type used by the API to calculate offsets.
message
language_service.proto:1018The entity analysis response message.
repeated entities = 1
The recognized entities in the input document.
string language = 2
The language of the text, which will be the same as the language specified in the request or, if not specified, the automatically-detected language. See [Document.language][google.cloud.language.v1.Document.language] field for more details.
Finds entities, similar to [AnalyzeEntities][google.cloud.language.v1.LanguageService.AnalyzeEntities] in the text and analyzes sentiment associated with each entity and its mentions.
message
language_service.proto:989The entity-level sentiment analysis request message.
optional document = 1
Input document.
EncodingType encoding_type = 2
The encoding type used by the API to calculate offsets.
message
language_service.proto:998The entity-level sentiment analysis response message.
repeated entities = 1
The recognized entities in the input document with associated sentiments.
string language = 2
The language of the text, which will be the same as the language specified in the request or, if not specified, the automatically-detected language. See [Document.language][google.cloud.language.v1.Document.language] field for more details.
Analyzes the syntax of the text and provides sentence boundaries and tokenization along with part of speech tags, dependency trees, and other properties.
message
language_service.proto:1029The syntax analysis request message.
optional document = 1
Input document.
EncodingType encoding_type = 2
The encoding type used by the API to calculate offsets.
message
language_service.proto:1038The syntax analysis response message.
repeated sentences = 1
Sentences in the input document.
repeated tokens = 2
Tokens, along with their syntactic information, in the input document.
string language = 3
The language of the text, which will be the same as the language specified in the request or, if not specified, the automatically-detected language. See [Document.language][google.cloud.language.v1.Document.language] field for more details.
Classifies a document into categories.
message
language_service.proto:1052The document classification request message.
optional document = 1
Input document.
message
language_service.proto:1058The document classification response message.
repeated categories = 1
Categories representing the input document.
A convenience method that provides all the features that analyzeSentiment, analyzeEntities, and analyzeSyntax provide in one call.
message
language_service.proto:1065The request message for the text annotation API, which can perform multiple analysis types (sentiment, entities, and syntax) in one call.
optional document = 1
Input document.
optional features = 2
The enabled features.
EncodingType encoding_type = 3
The encoding type used by the API to calculate offsets.
message
language_service.proto:1096The text annotations response message.
repeated sentences = 1
Sentences in the input document. Populated if the user enables [AnnotateTextRequest.Features.extract_syntax][google.cloud.language.v1.AnnotateTextRequest.Features.extract_syntax].
repeated tokens = 2
Tokens, along with their syntactic information, in the input document. Populated if the user enables [AnnotateTextRequest.Features.extract_syntax][google.cloud.language.v1.AnnotateTextRequest.Features.extract_syntax].
repeated entities = 3
Entities, along with their semantic information, in the input document. Populated if the user enables [AnnotateTextRequest.Features.extract_entities][google.cloud.language.v1.AnnotateTextRequest.Features.extract_entities].
optional document_sentiment = 4
The overall sentiment for the document. Populated if the user enables [AnnotateTextRequest.Features.extract_document_sentiment][google.cloud.language.v1.AnnotateTextRequest.Features.extract_document_sentiment].
string language = 5
The language of the text, which will be the same as the language specified in the request or, if not specified, the automatically-detected language. See [Document.language][google.cloud.language.v1.Document.language] field for more details.
repeated categories = 6
Categories identified in the input document.
message
language_service.proto:1068All available features for sentiment, syntax, and semantic analysis. Setting each one to true will enable that specific analysis for the input.
Used in:
bool extract_syntax = 1
Extract syntax information.
bool extract_entities = 2
Extract entities.
bool extract_document_sentiment = 3
Extract document-level sentiment.
bool extract_entity_sentiment = 4
Extract entities and their associated sentiment.
bool classify_text = 6
Classify the full document into categories.
message
language_service.proto:955Represents a category returned from the text classifier.
Used in: ,
string name = 1
The name of the category representing the document, from the [predefined taxonomy](/natural-language/docs/categories).
float confidence = 2
The classifier's confidence of the category. Number represents how certain the classifier is that this category represents the given text.
message
language_service.proto:652Represents dependency parse tree information for a token. (For more information on dependency labels, see http://www.aclweb.org/anthology/P13-2017
Used in:
int32 head_token_index = 1
Represents the head of this token in the dependency tree. This is the index of the token which has an arc going to this token. The index is the position of the token in the array of tokens returned by the API method. If this token is a root token, then the `head_token_index` is its own index.
DependencyEdge.Label label = 2
The parse label for the token.
The parse label enum for the token.
Used in:
UNKNOWN = 0
Unknown
ABBREV = 1
Abbreviation modifier
ACOMP = 2
Adjectival complement
ADVCL = 3
Adverbial clause modifier
ADVMOD = 4
Adverbial modifier
AMOD = 5
Adjectival modifier of an NP
APPOS = 6
Appositional modifier of an NP
ATTR = 7
Attribute dependent of a copular verb
AUX = 8
Auxiliary (non-main) verb
AUXPASS = 9
Passive auxiliary
CC = 10
Coordinating conjunction
CCOMP = 11
Clausal complement of a verb or adjective
CONJ = 12
Conjunct
CSUBJ = 13
Clausal subject
CSUBJPASS = 14
Clausal passive subject
DEP = 15
Dependency (unable to determine)
DET = 16
Determiner
DISCOURSE = 17
Discourse
DOBJ = 18
Direct object
EXPL = 19
Expletive
GOESWITH = 20
Goes with (part of a word in a text not well edited)
IOBJ = 21
Indirect object
MARK = 22
Marker (word introducing a subordinate clause)
MWE = 23
Multi-word expression
MWV = 24
Multi-word verbal expression
NEG = 25
Negation modifier
NN = 26
Noun compound modifier
NPADVMOD = 27
Noun phrase used as an adverbial modifier
NSUBJ = 28
Nominal subject
NSUBJPASS = 29
Passive nominal subject
NUM = 30
Numeric modifier of a noun
NUMBER = 31
Element of compound number
P = 32
Punctuation mark
PARATAXIS = 33
Parataxis relation
PARTMOD = 34
Participial modifier
PCOMP = 35
The complement of a preposition is a clause
POBJ = 36
Object of a preposition
POSS = 37
Possession modifier
POSTNEG = 38
Postverbal negative particle
PRECOMP = 39
Predicate complement
PRECONJ = 40
Preconjunt
PREDET = 41
Predeterminer
PREF = 42
Prefix
PREP = 43
Prepositional modifier
PRONL = 44
The relationship between a verb and verbal morpheme
PRT = 45
Particle
PS = 46
Associative or possessive marker
QUANTMOD = 47
Quantifier phrase modifier
RCMOD = 48
Relative clause modifier
RCMODREL = 49
Complementizer in relative clause
RDROP = 50
Ellipsis without a preceding predicate
REF = 51
Referent
REMNANT = 52
Remnant
REPARANDUM = 53
Reparandum
ROOT = 54
Root
SNUM = 55
Suffix specifying a unit of number
SUFF = 56
Suffix
TMOD = 57
Temporal modifier
TOPIC = 58
Topic marker
VMOD = 59
Clause headed by an infinite form of the verb that modifies a noun
VOCATIVE = 60
Vocative
XCOMP = 61
Open clausal complement
SUFFIX = 62
Name suffix
TITLE = 63
Name title
ADVPHMOD = 64
Adverbial phrase modifier
AUXCAUS = 65
Causative auxiliary
AUXVV = 66
Helper auxiliary
DTMOD = 67
Rentaishi (Prenominal modifier)
FOREIGN = 68
Foreign words
KW = 69
Keyword
LIST = 70
List for chains of comparable items
NOMC = 71
Nominalized clause
NOMCSUBJ = 72
Nominalized clausal subject
NOMCSUBJPASS = 73
Nominalized clausal passive
NUMC = 74
Compound of numeric modifier
COP = 75
Copula
DISLOCATED = 76
Dislocated relation (for fronted/topicalized elements)
ASP = 77
Aspect marker
GMOD = 78
Genitive modifier
GOBJ = 79
Genitive object
INFMOD = 80
Infinitival modifier
MES = 81
Measure
NCOMP = 82
Nominal complement of a noun
message
language_service.proto:106################################################################ # Represents the input to API methods.
Used in: , , , , ,
Document.Type type = 1
Required. If the type is not set or is `TYPE_UNSPECIFIED`, returns an `INVALID_ARGUMENT` error.
oneof source
The source of the document: a string containing the content or a Google Cloud Storage URI.
string content = 2
The content of the input in string format. Cloud audit logging exempt since it is based on user data.
string gcs_content_uri = 3
The Google Cloud Storage URI where the file content is located. This URI must be of the form: gs://bucket_name/object_name. For more details, see https://cloud.google.com/storage/docs/reference-uris. NOTE: Cloud Storage object versioning is not supported.
string language = 4
The language of the document (if not specified, the language is automatically detected). Both ISO and BCP-47 language codes are accepted.<br> [Language Support](/natural-language/docs/languages) lists currently supported languages for each API method. If the language (either specified by the caller or automatically detected) is not supported by the called API method, an `INVALID_ARGUMENT` error is returned.
The document types enum.
Used in:
TYPE_UNSPECIFIED = 0
The content type is not specified.
PLAIN_TEXT = 1
Plain text
HTML = 2
HTML
Represents the text encoding that the caller uses to process the output. Providing an `EncodingType` is recommended because the API provides the beginning offsets for various outputs, such as tokens and mentions, and languages that natively use different text encodings may access offsets differently.
Used in: , , , ,
NONE = 0
If `EncodingType` is not specified, encoding-dependent information (such as `begin_offset`) will be set at `-1`.
UTF8 = 1
Encoding-dependent information (such as `begin_offset`) is calculated based on the UTF-8 encoding of the input. C++ and Go are examples of languages that use this encoding natively.
UTF16 = 2
Encoding-dependent information (such as `begin_offset`) is calculated based on the UTF-16 encoding of the input. Java and JavaScript are examples of languages that use this encoding natively.
UTF32 = 3
Encoding-dependent information (such as `begin_offset`) is calculated based on the UTF-32 encoding of the input. Python is an example of a language that uses this encoding natively.
message
language_service.proto:162Represents a phrase in the text that is a known entity, such as a person, an organization, or location. The API associates information, such as salience and mentions, with entities.
Used in: , ,
string name = 1
The representative name for the entity.
Entity.Type type = 2
The entity type.
map<string, string> metadata = 3
Metadata associated with the entity. For most entity types, the metadata is a Wikipedia URL (`wikipedia_url`) and Knowledge Graph MID (`mid`), if they are available. For the metadata associated with other entity types, see the Type table below.
float salience = 4
The salience score associated with the entity in the [0, 1.0] range. The salience score for an entity provides information about the importance or centrality of that entity to the entire document text. Scores closer to 0 are less salient, while scores closer to 1.0 are highly salient.
repeated mentions = 5
The mentions of this entity in the input document. The API currently supports proper noun mentions.
optional sentiment = 6
For calls to [AnalyzeEntitySentiment][] or if [AnnotateTextRequest.Features.extract_entity_sentiment][google.cloud.language.v1.AnnotateTextRequest.Features.extract_entity_sentiment] is set to true, this field will contain the aggregate sentiment expressed for this entity in the provided document.
The type of the entity. For most entity types, the associated metadata is a Wikipedia URL (`wikipedia_url`) and Knowledge Graph MID (`mid`). The table below lists the associated fields for entities that have different metadata.
Used in:
UNKNOWN = 0
Unknown
PERSON = 1
Person
LOCATION = 2
Location
ORGANIZATION = 3
Organization
EVENT = 4
Event
WORK_OF_ART = 5
Artwork
CONSUMER_GOOD = 6
Consumer product
OTHER = 7
Other types of entities
PHONE_NUMBER = 9
Phone number<br><br> The metadata lists the phone number, formatted according to local convention, plus whichever additional elements appear in the text:<ul> <li><code>number</code> – the actual number, broken down into sections as per local convention</li> <li><code>national_prefix</code> – country code, if detected</li> <li><code>area_code</code> – region or area code, if detected</li> <li><code>extension</code> – phone extension (to be dialed after connection), if detected</li></ul>
ADDRESS = 10
Address<br><br> The metadata identifies the street number and locality plus whichever additional elements appear in the text:<ul> <li><code>street_number</code> – street number</li> <li><code>locality</code> – city or town</li> <li><code>street_name</code> – street/route name, if detected</li> <li><code>postal_code</code> – postal code, if detected</li> <li><code>country</code> – country, if detected</li> <li><code>broad_region</code> – administrative area, such as the state, if detected</li> <li><code>narrow_region</code> – smaller administrative area, such as county, if detected</li> <li><code>sublocality</code> – used in Asian addresses to demark a district within a city, if detected</li></ul>
DATE = 11
Date<br><br> The metadata identifies the components of the date:<ul> <li><code>year</code> – four digit year, if detected</li> <li><code>month</code> – two digit month number, if detected</li> <li><code>day</code> – two digit day number, if detected</li></ul>
NUMBER = 12
Number<br><br> The metadata is the number itself.
PRICE = 13
Price<br><br> The metadata identifies the <code>value</code> and <code>currency</code>.
message
language_service.proto:918Represents a mention for an entity in the text. Currently, proper noun mentions are supported.
Used in:
optional text = 1
The mention text.
EntityMention.Type type = 2
The type of the entity mention.
optional sentiment = 3
For calls to [AnalyzeEntitySentiment][] or if [AnnotateTextRequest.Features.extract_entity_sentiment][google.cloud.language.v1.AnnotateTextRequest.Features.extract_entity_sentiment] is set to true, this field will contain the sentiment expressed for this mention of the entity in the provided document.
The supported types of mentions.
Used in:
TYPE_UNKNOWN = 0
Unknown
PROPER = 1
Proper name
COMMON = 2
Common noun (or noun compound)
message
language_service.proto:322Represents part of speech information for a token. Parts of speech are as defined in http://www.lrec-conf.org/proceedings/lrec2012/pdf/274_Paper.pdf
Used in:
PartOfSpeech.Tag tag = 1
The part of speech tag.
PartOfSpeech.Aspect aspect = 2
The grammatical aspect.
PartOfSpeech.Case case = 3
The grammatical case.
PartOfSpeech.Form form = 4
The grammatical form.
PartOfSpeech.Gender gender = 5
The grammatical gender.
PartOfSpeech.Mood mood = 6
The grammatical mood.
PartOfSpeech.Number number = 7
The grammatical number.
PartOfSpeech.Person person = 8
The grammatical person.
PartOfSpeech.Proper proper = 9
The grammatical properness.
PartOfSpeech.Reciprocity reciprocity = 10
The grammatical reciprocity.
PartOfSpeech.Tense tense = 11
The grammatical tense.
PartOfSpeech.Voice voice = 12
The grammatical voice.
The characteristic of a verb that expresses time flow during an event.
Used in:
ASPECT_UNKNOWN = 0
Aspect is not applicable in the analyzed language or is not predicted.
PERFECTIVE = 1
Perfective
IMPERFECTIVE = 2
Imperfective
PROGRESSIVE = 3
Progressive
The grammatical function performed by a noun or pronoun in a phrase, clause, or sentence. In some languages, other parts of speech, such as adjective and determiner, take case inflection in agreement with the noun.
Used in:
CASE_UNKNOWN = 0
Case is not applicable in the analyzed language or is not predicted.
ACCUSATIVE = 1
Accusative
ADVERBIAL = 2
Adverbial
COMPLEMENTIVE = 3
Complementive
DATIVE = 4
Dative
GENITIVE = 5
Genitive
INSTRUMENTAL = 6
Instrumental
LOCATIVE = 7
Locative
NOMINATIVE = 8
Nominative
OBLIQUE = 9
Oblique
PARTITIVE = 10
Partitive
PREPOSITIONAL = 11
Prepositional
REFLEXIVE_CASE = 12
Reflexive
RELATIVE_CASE = 13
Relative
VOCATIVE = 14
Vocative
Depending on the language, Form can be categorizing different forms of verbs, adjectives, adverbs, etc. For example, categorizing inflected endings of verbs and adjectives or distinguishing between short and long forms of adjectives and participles
Used in:
FORM_UNKNOWN = 0
Form is not applicable in the analyzed language or is not predicted.
ADNOMIAL = 1
Adnomial
AUXILIARY = 2
Auxiliary
COMPLEMENTIZER = 3
Complementizer
FINAL_ENDING = 4
Final ending
GERUND = 5
Gerund
REALIS = 6
Realis
IRREALIS = 7
Irrealis
SHORT = 8
Short form
LONG = 9
Long form
ORDER = 10
Order form
SPECIFIC = 11
Specific form
Gender classes of nouns reflected in the behaviour of associated words.
Used in:
GENDER_UNKNOWN = 0
Gender is not applicable in the analyzed language or is not predicted.
FEMININE = 1
Feminine
MASCULINE = 2
Masculine
NEUTER = 3
Neuter
The grammatical feature of verbs, used for showing modality and attitude.
Used in:
MOOD_UNKNOWN = 0
Mood is not applicable in the analyzed language or is not predicted.
CONDITIONAL_MOOD = 1
Conditional
IMPERATIVE = 2
Imperative
INDICATIVE = 3
Indicative
INTERROGATIVE = 4
Interrogative
JUSSIVE = 5
Jussive
SUBJUNCTIVE = 6
Subjunctive
Count distinctions.
Used in:
NUMBER_UNKNOWN = 0
Number is not applicable in the analyzed language or is not predicted.
SINGULAR = 1
Singular
PLURAL = 2
Plural
DUAL = 3
Dual
The distinction between the speaker, second person, third person, etc.
Used in:
PERSON_UNKNOWN = 0
Person is not applicable in the analyzed language or is not predicted.
FIRST = 1
First
SECOND = 2
Second
THIRD = 3
Third
REFLEXIVE_PERSON = 4
Reflexive
This category shows if the token is part of a proper name.
Used in:
PROPER_UNKNOWN = 0
Proper is not applicable in the analyzed language or is not predicted.
PROPER = 1
Proper
NOT_PROPER = 2
Not proper
Reciprocal features of a pronoun.
Used in:
RECIPROCITY_UNKNOWN = 0
Reciprocity is not applicable in the analyzed language or is not predicted.
RECIPROCAL = 1
Reciprocal
NON_RECIPROCAL = 2
Non-reciprocal
The part of speech tags enum.
Used in:
UNKNOWN = 0
Unknown
ADJ = 1
Adjective
ADP = 2
Adposition (preposition and postposition)
ADV = 3
Adverb
CONJ = 4
Conjunction
DET = 5
Determiner
NOUN = 6
Noun (common and proper)
NUM = 7
Cardinal number
PRON = 8
Pronoun
PRT = 9
Particle or other function word
PUNCT = 10
Punctuation
VERB = 11
Verb (all tenses and modes)
X = 12
Other: foreign words, typos, abbreviations
AFFIX = 13
Affix
Time reference.
Used in:
TENSE_UNKNOWN = 0
Tense is not applicable in the analyzed language or is not predicted.
CONDITIONAL_TENSE = 1
Conditional
FUTURE = 2
Future
PAST = 3
Past
PRESENT = 4
Present
IMPERFECT = 5
Imperfect
PLUPERFECT = 6
Pluperfect
The relationship between the action that a verb expresses and the participants identified by its arguments.
Used in:
VOICE_UNKNOWN = 0
Voice is not applicable in the analyzed language or is not predicted.
ACTIVE = 1
Active
CAUSATIVE = 2
Causative
PASSIVE = 3
Passive
message
language_service.proto:149Represents a sentence in the input document.
Used in: , ,
optional text = 1
The sentence text.
optional sentiment = 2
For calls to [AnalyzeSentiment][] or if [AnnotateTextRequest.Features.extract_document_sentiment][google.cloud.language.v1.AnnotateTextRequest.Features.extract_document_sentiment] is set to true, this field will contain the sentiment for the sentence.
message
language_service.proto:308Represents the feeling associated with the entire text or entities in the text.
Used in: , , , ,
float magnitude = 2
A non-negative number in the [0, +inf) range, which represents the absolute magnitude of sentiment regardless of score (positive or negative).
float score = 3
Sentiment score between -1.0 (negative sentiment) and 1.0 (positive sentiment).
message
language_service.proto:945Represents an output piece of text.
Used in: , ,
string content = 1
The content of the output text.
int32 begin_offset = 2
The API calculates the beginning offset of the content in the original document according to the [EncodingType][google.cloud.language.v1.EncodingType] specified in the API request.
message
language_service.proto:292Represents the smallest syntactic building block of the text.
Used in: ,
optional text = 1
The token text.
optional part_of_speech = 2
Parts of speech tag for this token.
optional dependency_edge = 3
Dependency tree parse for this token.
string lemma = 4
[Lemma](https://en.wikipedia.org/wiki/Lemma_%28morphology%29) of the token.