Papers by Hussein Al-Olimat
A Practical Incremental Learning Framework For Sparse Entity Extraction (C18-1)
Copied to clipboard
| Challenge: | Existing approaches to extract entities from textual data are expensive and unattractive due to the high cost of training. |
| Approach: | They propose a framework that integrates Entity Set Expansion and Active Learning to reduce the cost of data annotation. |
| Outcome: | The proposed framework reduces the cost of sparse entity annotation by 85% and 45% while maintaining high accuracy. |
Location Name Extraction from Targeted Text Streams using Gazetteer-based Statistical Language Models (C18-1)
Copied to clipboard
| Challenge: | Location name extraction tool (LNEx) is a statistical language for extracting location names from informal and unstructured social media data. |
| Approach: | They propose a location name extraction tool that extracts location names from social media data . they use n-gram statistics and location-related dictionaries to evaluate an observed n in targeted text . |
| Outcome: | The proposed tool outperforms state-of-the-art taggers on 4,500 event-specific tweets . it improves the average F-Score by 33-179%, outperforming all tagger . |