An object-oriented model for semantic analysis of natural languages.
Material type:
TextDescription: 91 pISBN: 0493056890Subject(s): Computer Science | Language, Linguistics | 0984 | 0290Dissertation note: Thesis (M.S.)--King Fahd University of Petroleum and Minerals (Saudi Arabia), 2001. Summary: Natural Language Processing (NLP) has many applications such as Database user interfaces, Machine Translation, Knowledge Acquisition and Report Abstraction. Natural Language Processing can be subdivided into various stages. Semantic Analysis is regarded to be the most important and the most challenging stage. This stage concentrates on converting the input sentence into an internal representation that reflects the meaning of the sentence. Any NLP system relies on a lexicon that contains information about language vocabulary.Summary: The thesis proposes an Object-Oriented model for Semantic Analysis of Natural Languages. The model is named OSEMAN. OSEMAN assumes an object-oriented lexicon, where language words are stored as classes arranged in a semantic hierarchy. OSEMAN takes as input the stems of the sentence. Then it instantiates the steins from the sentence. These stems are combined to form an internal representation that reflects the meaning of the input sentence. These stems may combine in different ways that yields more than one internal representation for the same input sentence. Each representation is quantified by an overall weight that reflects the semantic consistency between the stems of the sentence.
Source: Masters Abstracts International, Volume: 39-03, page: 0875.
Thesis (M.S.)--King Fahd University of Petroleum and Minerals (Saudi Arabia), 2001.
Natural Language Processing (NLP) has many applications such as Database user interfaces, Machine Translation, Knowledge Acquisition and Report Abstraction. Natural Language Processing can be subdivided into various stages. Semantic Analysis is regarded to be the most important and the most challenging stage. This stage concentrates on converting the input sentence into an internal representation that reflects the meaning of the sentence. Any NLP system relies on a lexicon that contains information about language vocabulary.
The thesis proposes an Object-Oriented model for Semantic Analysis of Natural Languages. The model is named OSEMAN. OSEMAN assumes an object-oriented lexicon, where language words are stored as classes arranged in a semantic hierarchy. OSEMAN takes as input the stems of the sentence. Then it instantiates the steins from the sentence. These stems are combined to form an internal representation that reflects the meaning of the input sentence. These stems may combine in different ways that yields more than one internal representation for the same input sentence. Each representation is quantified by an overall weight that reflects the semantic consistency between the stems of the sentence.
School code: 1088.
There are no comments on this title.