![]() | Only 14 pages are availabe for public view |
Abstract Variability of semantic expression is a fundamental phenomenon of a natural language where same meaning can be expressed by different texts. The process of inferring a text from another is called Textual Entailment. Textual Entailment is useful in a wide range of applications, including question answering, summarization, text generation, and machine translation. The textual entailment Recognition is one of the recent challenges of the Natural Language Processing (NLP) domain. Textual entailment (TE) is a relation that holds between two pieces of text, where if one read the first piece can conclude that the second is most likely true. It can help in various natural language processing (NLP) applications as explained above. So, researches on textual entailment attracted a significant amount of attention in recent years. Researchers have worked on Recognizing Textual Entailment (RTE), since 2005 [1]. .~ The main objective of this thesis is to propose an effective model to Textual Entailment Recognition, such that given a sentence pair (a, b), the task is to predict whether b is entailed or not by a. A spectrum of approaches has been proposed for Recognizing Textual Entailment (RTE). Most of RTE systems are. based on Machine Learning, lexical or semantic approaches [2]. However, the entailment decision problem can be considered as a classification problem. Such systems use features such as lexical, syntactic and semantic features. The proposed Textual Entailment Recognition model is based on hybrid approach which consists of Preprocessing, lexical, syntactic, semantic analysis and Deep Learning classifier entailment module. The proposed model consists from 5 components, it starts with preprocessing component and ends with Deep learning classifier, between them there are lexical, syntactic and semantic analysis components. Some of those components can be separated and used in textual entailment recognition solely. Lexical analysis is used only a lexical representation of the sentences to compare lexical items. It is based on lexicographic matching between terms. |