Loading...
Please wait, while we are loading the content...
Similar Documents
Size of N for Word Sense Disambiguation using N gram model for Punjabi Language
| Content Provider | Semantic Scholar |
|---|---|
| Author | Josan, Gurpreet Singh Lehal, Gurpreet Singh |
| Copyright Year | 2008 |
| Abstract | N-grams are consecutive overlapping N-character sequences formed from an input stream. N-gram models are extensively used in word sense disambiguation. In this paper we tried to find out whether higher order n gram models improves the word sense disambiguation in Punjabi language and whether it has any relation with entropy of the models. In our experiments statistical analysis of n gram models for n ranging from ±1 to ±6 is done. We also tried to explore the possibility of disambiguation by using future knowledge. From this experiment it became clear that lower order n gram models are sufficient for word sense disambiguation and larger n gram model gives little improvement. Disambiguation with the help of future knowledge also gives promising results. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://learnpunjabi.org/pdf/gslehal-pap19.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
