
handle: 10045/1667
La resolución de la ambigüedad léxica es una tarea importante dentro del procesamiento del lenguaje natural. En este trabajo, se presenta un nuevo enfoque basado en redes neuronales para aumentar la precisión en la tarea de desambiguación. Concretamente, se utiliza el algoritmo de aprendizaje basado en el modelo de Kohonen conocido con el nombre de algoritmo de aprendizaje por cuantificación vectorial LVQ (Learning Vector Quatization). Los resultados obtenidos demuestran que la utilización de dicho algoritmo competitivo supera notablemente a otros algoritmos ampliamente utilizados en otros trabajos.
Word Sense Disambiguation is an important task in Natural Language Processing. This work shows a new approach based on neuronal networks that increases the precision in WSD task. The learning algorithm is based on the Kohonen model, known with the name of the LVQ algorithm (Learning Vector Quatization). The results demonstrate that the use of this competitive algorithm performes better than other algorithms widely used in other works.
LVQ algorithm, Redes neuronales artificiales, Artificial neural networks, WSD, Algoritmo LVQ, SemCor
LVQ algorithm, Redes neuronales artificiales, Artificial neural networks, WSD, Algoritmo LVQ, SemCor
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
