Paronym Generation Algorithms for Malapropism Correction
Journal Title: Romanian Journal of Human - Computer Interaction - Year 2008, Vol 1, Issue 1
Abstract
The Web pages have been intensively used lately for automatic or semiautomatic extraction of useful information. Because of the open nature of the Web, the texts that have no spelling errors are very rare exceptions. One of the most wide-spread errors in Internet texts is the malapropism. Thus, malapropism detection and correction algorithms have been investigated. The detection algorithms are based on text cohesion while the correction algorithms use precompiled paronyms dictionaries. Therefore, it is very important to identify efficient algorithms for generating paronyms. In the present paper, we make an overview presentation of the paronyms and of the methods that can be used in order to build a paronyms dictionary. A presentation of the main errors that can lead to malapropism is also provided and the way these errors can be corrected using a paronyms dictionary is suggested.
Authors and Affiliations
Costin-Gabriel Chiru, Ştefan Trăuşan-Matu, Traian Rebedea
Kinect v2 evaluation for in-home medical rehabilitation scenarios
The technology advancements greatly improved the medical services over time with virtual reality (VR) devices and applications. Currently taking advantage of these recent advancements is the medical rehabilitation field,...
Analytical platform for the study of usage data generated by telemedicine services
Telemedicine researches nowadays focus more and more on the complexity of the services that can be delivered and on the development of new paradigms of healthcare delivery. The paper proposes a different approach, a stud...
Towards a Culture-Adaptable User-Interface Architecture
Culture plays a role in the way humans interact with the machine. It implies changes on the UI to fit cultural needs, practices and preferences. Knowledge on these implications is sparse and insufficient until the mome...
News Web Portal based on Natural Language Processing
The paper presents an autonomous text classification module for a news web portal for the Romanian language. Statistical natural language processing techniques are combined in order to achieve a completely autonomous fun...
Integrating 3D Scene in Interactive Graphics Applications
Building and using tridimensional geometric models in computer applications imply great efforts in production software application. A model contains both complex geometry and properties such as color, lighting, texture,...