dbo:abstract |
In machine learning, semantic analysis of a corpus is the task of building structures that approximate concepts from a large set of documents. It generally does not involve prior semantic understanding of the documents. A metalanguage based on predicate logic can analyze the speech of humans. Another strategy to understand the semantics of a text is symbol grounding. If language is grounded, it is equal to recognizing a machine readable meaning. For the restricted domain of spatial analysis, a computer based language understanding system was demonstrated. Latent semantic analysis (sometimes latent semantic indexing), is a class of techniques where documents are represented as vectors in term space. A prominent example is PLSI. Latent Dirichlet allocation involves attributing document terms to topics. n-grams and hidden Markov models work by representing the term stream as a Markov chain where each term is derived from the few terms before it. (en) 語意分析(semantic analysis)技術是指將一長串的文字或內容,從其中分析出該個段落的摘要以及大意,甚至更進一步,將整篇文章的文意整理出來。此項技術可以應用在解讀影片、音訊等檔案,使得搜尋引擎能夠搜尋到文字以外的物件,方便使用者省去大量時間觀看影片、聆聽音訊,同時也可以幫助使用者提前了解影片與音訊的內容。 語意分析技術在早期基於奇異值分解(Singular Value Decomposition, SVD)、非負矩陣拆解法(Non-negative matrix factorization,NMF)等方式,近年來則有用各種型態的類神經網絡(Neural Network, NN)來完成語意分析的目的。 (zh) |
dbo:wikiPageID |
14271782 (xsd:integer) |
dbo:wikiPageLength |
1977 (xsd:nonNegativeInteger) |
dbo:wikiPageRevisionID |
1095848084 (xsd:integer) |
dbo:wikiPageWikiLink |
dbr:Predicate_logic dbr:N-gram dbr:Ontology_learning dbr:Information_extraction dbr:Linear_algebra dbr:Machine_learning dbr:Probabilistic_latent_semantic_indexing dbc:Machine_learning dbr:Latent_Dirichlet_allocation dbr:Latent_semantic_analysis dbr:Text_corpus dbr:Symbol_grounding dbr:Metalanguage dbr:Markov_chain dbr:Semantic_similarity dbr:Explicit_semantic_analysis dbr:Hidden_Markov_models |
dbp:wikiPageUsesTemplate |
dbt:Compsci-stub dbt:Annotated_link dbt:More_citations_needed dbt:Other_uses dbt:Reflist dbt:Rp dbt:Semantics |
dct:subject |
dbc:Machine_learning |
gold:hypernym |
dbr:Task |
rdf:type |
dbo:Agent |
rdfs:comment |
語意分析(semantic analysis)技術是指將一長串的文字或內容,從其中分析出該個段落的摘要以及大意,甚至更進一步,將整篇文章的文意整理出來。此項技術可以應用在解讀影片、音訊等檔案,使得搜尋引擎能夠搜尋到文字以外的物件,方便使用者省去大量時間觀看影片、聆聽音訊,同時也可以幫助使用者提前了解影片與音訊的內容。 語意分析技術在早期基於奇異值分解(Singular Value Decomposition, SVD)、非負矩陣拆解法(Non-negative matrix factorization,NMF)等方式,近年來則有用各種型態的類神經網絡(Neural Network, NN)來完成語意分析的目的。 (zh) In machine learning, semantic analysis of a corpus is the task of building structures that approximate concepts from a large set of documents. It generally does not involve prior semantic understanding of the documents. A metalanguage based on predicate logic can analyze the speech of humans. Another strategy to understand the semantics of a text is symbol grounding. If language is grounded, it is equal to recognizing a machine readable meaning. For the restricted domain of spatial analysis, a computer based language understanding system was demonstrated. (en) |
rdfs:label |
Semantic analysis (machine learning) (en) 語意分析 (zh) |
owl:sameAs |
freebase:Semantic analysis (machine learning) wikidata:Semantic analysis (machine learning) dbpedia-zh:Semantic analysis (machine learning) https://global.dbpedia.org/id/4uPvP |
prov:wasDerivedFrom |
wikipedia-en:Semantic_analysis_(machine_learning)?oldid=1095848084&ns=0 |
foaf:isPrimaryTopicOf |
wikipedia-en:Semantic_analysis_(machine_learning) |
is dbo:wikiPageDisambiguates of |
dbr:Semantic_analysis |
is dbo:wikiPageRedirects of |
dbr:Semantic_analysis_(informatics) |
is dbo:wikiPageWikiLink of |
dbr:International_Conference_on_Computatio...stics_and_Intelligent_Text_Processing dbr:Rada_Mihalcea dbr:Concept_search dbr:Chatbot dbr:Google_Hummingbird dbr:Highway_network dbr:National_Centre_for_Text_Mining dbr:Networked_Insights dbr:Semantic_analysis dbr:Semantic_analysis_(computational) dbr:Semantic_analysis_(knowledge_representation) dbr:Semantic_analysis_(linguistics) dbr:Outline_of_machine_learning dbr:Semantic_analysis_(informatics) |
is foaf:primaryTopic of |
wikipedia-en:Semantic_analysis_(machine_learning) |