Meaning representation in natural language processing
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...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
2015
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/62780 |
| Summary: | 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. |
|---|