An associative method for Lesk-based word sense disambiguation
Abstract One of the most important current problems in natural language processing is word sense disambiguation (WSD). WSD consists of identifying the correct sense of the words in a given text. In this work, we present a novel method for automatic WSD based on the simplified-Lesk algorithm. The proposed method employs Alpha-Beta associative memories for the relatedness computation between the senses of the ambiguous words and its context. The performance of this method was evaluated in terms of precision, recall, and F-score, using the semantically annotated corpora Senseval-2, Semcor, and Semeval-2007. The results show the advantages of the proposed method compared with other Lesk-based state-of-the-art methods.
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Digital revista |
| Language: | English |
| Published: |
Pontificia Universidad Católica de Valparaíso. Instituto de Literatura y Ciencias del Lenguaje
2017
|
| Online Access: | http://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0718-09342017000200287 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract One of the most important current problems in natural language processing is word sense disambiguation (WSD). WSD consists of identifying the correct sense of the words in a given text. In this work, we present a novel method for automatic WSD based on the simplified-Lesk algorithm. The proposed method employs Alpha-Beta associative memories for the relatedness computation between the senses of the ambiguous words and its context. The performance of this method was evaluated in terms of precision, recall, and F-score, using the semantically annotated corpora Senseval-2, Semcor, and Semeval-2007. The results show the advantages of the proposed method compared with other Lesk-based state-of-the-art methods. |
|---|