Textual Entailment based on Semantic Similarity Using WordNet
| Autor: | R. Shreelekshmi, S. Nishy Reshmi |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Scheme (programming language)
business.industry Computer science InformationSystems_INFORMATIONSTORAGEANDRETRIEVAL Cosine similarity WordNet Computer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing) 02 engineering and technology Similarity measure computer.software_genre Logical consequence 03 medical and health sciences 0302 clinical medicine Semantic similarity 030221 ophthalmology & optometry 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business Textual entailment computer Natural language processing Sentence computer.programming_language |
| Zdroj: | 2019 2nd International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT). |
| DOI: | 10.1109/icicict46008.2019.8993180 |
| Popis: | We propose a method for automatic recognition of textual entailment based on word sense disambiguation using cosine similarity proposed by Abdalgader and Skabar. This algorithm finds semantic similarity of the sentence pairs- entailing text and entailed text. Both the hypothesis and text are converted into vectors using Jiang and Conrath similarity measure and cosine similarity is computed. Based on the cosine similarity score, a threshold is applied and the sentence pairs are classified into entailment and no entailment. The accuracy of the proposed scheme is better or comparable to many of the state of the art schemes. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|