Loading...
| Friend's email | |
| Your name | |
| Your email | |
| enter code | |
This page was sent successfuly
- Type of Document: M.Sc. Thesis
- Language: Farsi
- Document No: 50745 (31)
- University: Sharif University of Technology
- Department: Languages and Linguistics
- Advisor(s): Izadi, Mohammad
- Abstract:
- Paraphrases are sentences or phrases, which convey the same meaning using different words. There are different definitions for paraphrasing and most linguists believe that, paraphrases approximately equivalent in meaning. Paraphrase recognition is useful in different natural language processing areas such as question answering, information extraction, plagiarism recognition and machine translation. In this thesis, the purpose is to present a method for paraphrase recognition, using deep semantic analysis and meaning representation of sentences. To achieve this purpose first, meaning features were defined for every syntactic category and semantic analysis of sentences alongside mapping of natural language phrases to first order logic, in which analysis is possible, was done. Then, syntactic trees of sentences were acquired to represent sentence components and the way they are combined. After that, by using event semantic and Neo-Davisonian method for semantic analysis of sentences, semantic representation of Persian sentences were attained in first order logic. With extraction of sense relation between words and phrases from knowledge bases, an automated theorem prover investigates the results of meaning representations and semantic structure of sentences. sentence pairs in Degarbayan Corpus were used for evaluating and covering language capability. Finally, meaning representaion for these sentences were acquired and Then with considering sense relation of words, truth or falsity of paraphrase relations of sentences was specified
- Keywords:
- Paraphrase ; Persian Paraphrase Recognition ; Meaning Representation ; Semantic Analysis ; Event Semantic
Digital Object List
-
محتواي کتاب
- view
Bookmark