Meaning representation in natural language processing

• Main Author: Tan, Shermaine
• Other Authors: Kim Jung-Jae
• Format: Final Year Project
• Language: English
• Published: 2015
• Subjects: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
• Online Access: http://hdl.handle.net/10356/62780
• Institution: Nanyang Technological University

This report will outline the performance and accuracy using Extreme Learning Machine on Matlab. Data from the weScience corpus was used to carry out feature engineering using a Python software model carried over from a past project. The semantic features generated are first passed into a Java class for pre-processing before using it for training and testing purposes using the Extreme Learning Machine. At the end, results for the various sets of data will be presented using Root-Mean-Squared Errors (RMSE) and Normalised Root-Mean-Squared Errors (NRMSE) values.