What makes sense? Searching for strong WSD predictors in Croatian
The goal of this research was to investigate and determine position of strong predictors for word sense disambiguation of Croatian nouns. // Research was conducted using supervised learning methods and a corpus of around 70 million words. We have concluded that words in the immediate vicinity of an...
| Permalink: | http://skupni.nsk.hr/Record/ffzg.KOHA-OAI-FFZG:311865/Details |
|---|---|
| Matična publikacija: |
Digital information and heritage 592 |
| Glavni autori: | Bakarić, Nikola (-), Njavro, Jasmina (Author), Ljubešić, Nikola |
| Vrsta građe: | Članak |
| Jezik: | eng |
| LEADER | 01768naa a2200253uu 4500 | ||
|---|---|---|---|
| 008 | 131111s2007 xx eng|d | ||
| 020 | |a 978953-175-305-0 | ||
| 035 | |a (CROSBI)348544 | ||
| 040 | |a HR-ZaFF |b hrv |c HR-ZaFF |e ppiak | ||
| 100 | 1 | |a Bakarić, Nikola | |
| 245 | 1 | 0 | |a What makes sense? Searching for strong WSD predictors in Croatian / |c Bakarić, Nikola ; Njavro, Jasmina ; Ljubešić, Nikola. |
| 246 | 3 | |i Naslov na engleskom: |a What makes sense? Searching for strong WSD predictors in Croatian | |
| 300 | |a 321-326 |f str. | ||
| 520 | |a The goal of this research was to investigate and determine position of strong predictors for word sense disambiguation of Croatian nouns. // Research was conducted using supervised learning methods and a corpus of around 70 million words. We have concluded that words in the immediate vicinity of an observed lexeme (1-5 words left and right) have the highest discriminative power. We have also measured the applicability and accuracy of the one-sense- per-discourse method and found it to be very successful as well as the impact of sentence boundaries which proved not to be a good criterion for selecting strong predictors. | ||
| 536 | |a Projekt MZOS |f 130-1301679-1380 | ||
| 546 | |a ENG | ||
| 690 | |a 5.04 | ||
| 693 | |a word sense disambiguation, Croatian language, strong predictors |l hrv |2 crosbi | ||
| 693 | |a word sense disambiguation, Croatian language, strong predictors |l eng |2 crosbi | ||
| 700 | 1 | |a Njavro, Jasmina |4 aut | |
| 700 | 1 | |a Ljubešić, Nikola |4 aut | |
| 773 | 0 | |t Digital information and heritage |d Zagreb : Odsjek za informacijske znanosti Filozofskog fakulteta u Zagrebu, 2007 |h 592 |n Seljan, Sanja ; Stančić, Hrvoje |z 978-953-175-305-0 |g str. 321-326 | |
| 942 | |c POG |t 1.16.1 |u 1 |z Znanstveni | ||
| 999 | |c 311865 |d 311863 | ||