Word sense disambiguation based on lexical weighting in conceptual density
Publish place: The first international conference of modern research engineers in electricity and computer
Publish Year: 1395
نوع سند: مقاله کنفرانسی
زبان: English
View: 685
This Paper With 5 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
CBCONF01_0127
تاریخ نمایه سازی: 16 شهریور 1395
Abstract:
In this paper, examining the key role of the noun in the lexical disambiguaty of English text, a new method of combining conceptual density method with giving weights to some unambiguous nouns in COCA Corpus and Brown Corpus for word sense disambiguation is presented. In this method, as well as conceptual density, the focus is on the most covered nouns in the hierarchical structure of WordNet, with the difference expressing the weight is given based on three parameters to unambiguous nouns while the process of disambiguation is done based upon them. So nouns with more semantic closeness to the ambiguous noun, have more impact on the disambiguation process. The results of conducted studies using these three weighting parameter, either separately or in combination indicating an acceptable level of accuracy in disambiguation.
Keywords:
Authors
Ali Golkar
Young Researchers and Elite Club, Zahedan Branch, Islamic Azad University Zahedan, Iran
Pouneh Janmohammadi
Department of Computer, Babol Branch, Islamic Azad University Babol, Iran
Mohammad Reza Parsaei
Shiraz University of Technology, Department of Computer Engineering and IT, Shiraz, Iran
Mohammad Javad Golkar
Department of Electrical & Computer Engineering, Payam Noor University (PNU) Iran
Azita Yazdani
Department of Paramedical sciences, Tehran University, Tehran, Iran
مراجع و منابع این Paper:
لیست زیر مراجع و منابع استفاده شده در این Paper را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود Paper لینک شده اند :