RepositoryWebrefEntityAnnotations

AI Overview😉

The potential purpose of this module is to analyze and understand the relationship between a given concept (entity) and a document or query. It appears to be a part of Google's natural language processing (NLP) and information retrieval system, aiming to identify and rank entities mentioned in a document or query based on their relevance and importance.
This module could impact search results by influencing the ranking of web pages based on the relevance and importance of entities mentioned in the content. It may also affect the accuracy of query interpretation and the identification of relevant entities in search queries. The module's output could be used to improve the search engine's understanding of user intent and provide more accurate and relevant search results.
To be more favorable for this function, a website could focus on: Clearly mentioning and highlighting relevant entities in the content, especially in titles, headings, and anchors. Ensuring that the content is well-structured and easy to understand, which could improve the accuracy of entity identification and ranking. Providing high-quality and relevant images that are properly tagged and described, which could improve the imageMention feature. Using natural language and avoiding ambiguity in the content, which could improve the accuracy of query interpretation and entity resolution.

Interesting Module? Vote 👇

Voting helps other researchers find interesting modules.

Current Votes: 0

GoogleApi.ContentWarehouse.V1.Model.RepositoryWebrefEntityAnnotations (google_api_content_warehouse v0.4.0)

All annotations for a given concept (in one document collection). Available tags: [10-15], [19-]

Attributes

confidenceScore (type: number(), default: nil) - The overall confidence that the entity is annotated somewhere in the document or query. For WebRef it is computed as a function of the mention confidences weighted by the importance of each mention, where for documents a mention is of greater importance if it occurs in the title, h1 or anchors. For QRef it is just the maximum of the confidence over all mentions. NOTE: You probably want to use the mention-level segment_mentions.mention.confidence_score field instead of this one.
debugInfo (type: GoogleApi.ContentWarehouse.V1.Model.RepositoryWebrefAnnotationDebugInfo.t, default: nil) -
detailedEntityScores (type: GoogleApi.ContentWarehouse.V1.Model.RepositoryWebrefDetailedEntityScores.t, default: nil) - Additional information about how the entity relates to the page, for example whether it is a business entity which published the page.
explainedRangeInfo (type: GoogleApi.ContentWarehouse.V1.Model.RepositoryWebrefExplainedRangeInfo.t, default: nil) - All ranges explained by the entity or any other entity it implies. Used in the context of partial query interpretation (go/partial-understanding).
imageMention (type: list(GoogleApi.ContentWarehouse.V1.Model.RepositoryWebrefImageMention.t), default: nil) - This is an experimental output for go/multiref. Don't use it without consulting the Webref team
isImplicit (type: boolean(), default: nil) - An entity is marked as implicit if there is no explicit mention of the entity in the content of the page. For instance, all mentions of the entity are in query, url and/or anchors; or the entity has only implicit content mentions.
isResolution (type: boolean(), default: nil) - True if the entity is an MDVC summary entity, i.e. it might not be mentioned directly on the query, but it is the product of resolving a set of explicit annotations. E.g. "2014 FIFA World Cup" can be the summary for the query: [soccer world cup in brazil] even though none of the names of the entity is mentioned on the query. Summary nodes can also be synthetic, i.e. have a /t/ mid, as they represent the intersection between a set of regular annotations. For more information, see http://go/mdvc-output.
segmentMentions (type: list(GoogleApi.ContentWarehouse.V1.Model.RepositoryWebrefSegmentMentions.t), default: nil) - All mentions of a given concept grouped by segments. For Webref, there are many different kinds of segment, such as content, title and anchors; while for QRef, there is only one segment called CONTENT. For QRef this field contains the primary output of the annotator, and for WebRef it together with topicality_score does.
topicalityRank (type: integer(), default: nil) - Rank of the entity when sorted by topicality score.
topicalityScore (type: number(), default: nil) - The WebRef topicality score of the entity for this document. This score indicates how related is the entity to the overall topic of the document. See https://goto.google.com/topicality-score for details. This field is not present in QRef output. Note that the topicality and the confidence score are orthogonal measures. It is possible that the annotator is absolutely sure that an entity is mentioned in a given range in the document, but this entity may be unrelated to the overall topic of the page (e.g. the entity "RSS" is mentioned in the footer of appleinsider.com). In this case the mention has a very high confidence score, but very low topicality score.

Summary

Types

t()

Functions

decode(value, options)

Unwrap a decoded JSON object into its complex fields.

Types

Link to this type

t()

@type t() :: %GoogleApi.ContentWarehouse.V1.Model.RepositoryWebrefEntityAnnotations{
  confidenceScore: number() | nil,
  debugInfo:
    GoogleApi.ContentWarehouse.V1.Model.RepositoryWebrefAnnotationDebugInfo.t()
    | nil,
  detailedEntityScores:
    GoogleApi.ContentWarehouse.V1.Model.RepositoryWebrefDetailedEntityScores.t()
    | nil,
  explainedRangeInfo:
    GoogleApi.ContentWarehouse.V1.Model.RepositoryWebrefExplainedRangeInfo.t()
    | nil,
  imageMention:
    [GoogleApi.ContentWarehouse.V1.Model.RepositoryWebrefImageMention.t()] | nil,
  isImplicit: boolean() | nil,
  isResolution: boolean() | nil,
  segmentMentions:
    [GoogleApi.ContentWarehouse.V1.Model.RepositoryWebrefSegmentMentions.t()]
    | nil,
  topicalityRank: integer() | nil,
  topicalityScore: number() | nil
}

Functions

Link to this function

decode(value, options)

@spec decode(struct(), keyword()) :: struct()

Unwrap a decoded JSON object into its complex fields.