Verdezoto, Nervo ![]() |
Official URL: https://dl.acm.org/doi/10.5555/2002669.2002698
Abstract
WordNet is extensively used as a major lexical resource in NLP. However, its quality is far from perfect, and this alters the results of applications using it. We propose here to complement previous efforts for "cleaning up" the top-level of its taxonomy with semi-automatic methods based on the detection of errors at the lower levels. The methods we propose test the coherence of two sources of knowledge, exploiting ontological principles and semantic constraints.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Status: | Published |
Schools: | Computer Science & Informatics |
Publisher: | ACM |
Date of First Compliant Deposit: | 21 March 2021 |
Last Modified: | 09 Nov 2022 10:35 |
URI: | https://orca.cardiff.ac.uk/id/eprint/139979 |
Actions (repository staff only)
![]() |
Edit Item |