Enhancement of Hybrid Tagger by using Rule Based Approach
| Autor: | Pratik K. Agrawal, A. S. Alvi, G. R. Bamnote |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Recall
business.industry Computer science Speech recognition InformationSystems_INFORMATIONSTORAGEANDRETRIEVAL WordNet Rule-based system 02 engineering and technology English language computer.software_genre 030507 speech-language pathology & audiology 03 medical and health sciences 020204 information systems Trigram tagger 0202 electrical engineering electronic engineering information engineering Artificial intelligence 0305 other medical science business computer Natural language processing |
| Zdroj: | Proceedings of the Second International Conference on Information and Communication Technology for Competitive Strategies. |
| DOI: | 10.1145/2905055.2905227 |
| Popis: | Public opinions, reviews and open discussion are the best source of getting the feedback for the products and services to the developer for further improvement. Advance development of the world has brought the people close to each other and the feedbacks are carried out electronically via different medium. The feedback or opinions are mostly in the form of free textual form. People express their views and feelings in their own language. The natural language processing is required for the analysis of this data. The pos tagging is the important step in NLP for carrying out the processing. In this paper, we have developed hybrid tagger for the English language that uses the rule based approach in combination with oxford and WordNet dictionary. The proposed tagger is compared with different tagger available for English language. The Performance of the proposed tagger compare with the other tagger in terms of precision, recall and accuracy provide efficient accuracy and satisfactory result. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|