Wyniki wyszukiwania:

The main aim of this work is to design online textual presentation by using various approaches like information retrieval, information extraction, topic identification and sentence weightage algorithms. This helps in reducing the time for preparing a presentation. The textual presentation file will be generated for the user's topic of interest. The user has to provide the title and purpose for which presentation is to be built. The user query is sent to the search engine. The files related to the information's in the various formats are collected and converted to text file. The converted...

This work focuses on the construction of an automatic ontology tree which is capable of dynamically updating information for efficient management of up-to-date information in the domain of mobile phones. The proposed system takes the URL of the most relevant website as input. It acquires information from web pages that are related to the domain. This information is acquired from web pages using pattern matching and jSoup parsing technique, and the ontology tree is constructed automatically without manual labour as in a manual or semi-automatic ontology. To make sure that the ontology...

This thesis proposes a new approach to improve the performance of Tamil speech recognition using language models. The main contribution of this thesis is the development of language models to capture co-occurrence patterns of partially free word order languages like Tamil. The models designed used sub-word units such as phonemes, syllables and morphemes as basic components of the language model. In addition the thesis explains the use of various language models at different levels of error correction. Language models based on different sub-word units, sub-word unit features and contexts...