Adding Morphological Information to a Connectionist Part-Of-Speech Tagger
| Autor: | Salvador España-Boquera, Maria Jose Castro-Bleda, Salvador Tortajada-Velert, Francisco Zamora-Martínez |
|---|---|
| Rok vydání: | 2010 |
| Předmět: |
Artificial neural network
business.industry Computer science Speech recognition Treebank Part of speech computer.software_genre Perceptron ComputingMethodologies_ARTIFICIALINTELLIGENCE ComputingMethodologies_PATTERNRECOGNITION Connectionism Artificial intelligence business computer Tag system Natural language processing |
| Zdroj: | Current Topics in Artificial Intelligence ISBN: 9783642142635 CAEPIA |
| DOI: | 10.1007/978-3-642-14264-2_20 |
| Popis: | In this paper, we describe our recent advances on a novel approach to Part-Of-Speech tagging based on neural networks. Multilayer perceptrons are used following corpus-based learning from contextual, lexical and morphological information. The Penn Treebank corpus has been used for the training and evaluation of the tagging system. The results show that the connectionist approach is feasible and comparable with other approaches. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|