Implementation Paper on Document Recommendation in Conversations
Journal: International Journal of Engineering and Techniques (Vol.2, No. 3)Publication Date: 2016-05-01
Authors : Anshika Sujit Tak Sandeep Ugale Abhishek Pohekar;
Page : 76-82
Keywords : Document recommendation; information retrieval; keyword extraction.;
Abstract
This paper is focused towards extraction of important words from conversations, and then these words are utilized to recover a small number of relevant documents, which can be given to users as per their needs. In any case, even a short audio fragment contains of large number of words, which are conceivably identified with a few topics and also, using automatic speech recognition (ASR) framework reduces errors in the output. It is difficult to provide the data needs of the conversation members appropriately. A calculation to remove decisive words from the yield of an ASR framework (or a manual transcript for testing) to support the potentially differing qualities of subjects and decrease ASR commotion is proposed. At that point, a technique is used to make many implicit queries from the selected keywords. These queries will in return produce list of relevant documents. The scores demonstrate that our proposition is modified over past systems that consider just word re-occurrence or topic closeness, and speaks to an appropriate answer for a report recommender framework to be utilized as a part of discussions.
Other Latest Articles
- Exponential Stabilization of the Coupled Dynamical Neural Networks with Nodes of Different Dimensions and Time Delays
- An Optimal Approach for Secure and Energy Efficient Data Transfer in WSN using Hierarchical and Dynamic Elliptic Curve Cryptosystem
- Molecular dynamics Parallel simulation of Carbon Nanotubes based on GPU
- A Comparative Analysis of Three Phase Induction Motor Performance Evaluation
- Review Paper: Hybrid Amplifiers in FSO System
Last modified: 2018-05-18 19:27:11