Addressing polysemy in bilingual lexicon extraction from comparable corpora
This paper presents an approach to extract translation equivalents from comparable corpora for polysemous nouns. As opposed to the standard approaches that build a single context vector for all occurrences of a given headword, we first disambiguate the headword with third-party sense taggers and the...
| Permalink: | http://skupnikatalog.nsk.hr/Record/ffzg.KOHA-OAI-FFZG:318225/Details |
|---|---|
| Matična publikacija: |
Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC'12) Istanbul : 2012 |
| Glavni autori: | Fišer, Darja (-), Kubelka, Ozren (Author), Ljubešić, Nikola, informatičar |
| Vrsta građe: | Članak |
| Jezik: | eng |
| Online pristup: |
http://www.lrec-conf.org/proceedings/lrec2012/index.html |
| LEADER | 02185naa a2200265uu 4500 | ||
|---|---|---|---|
| 008 | 131111s2012 xx 1 eng|d | ||
| 035 | |a (CROSBI)616769 | ||
| 040 | |a HR-ZaFF |b hrv |c HR-ZaFF |e ppiak | ||
| 100 | 1 | |a Fišer, Darja | |
| 245 | 1 | 0 | |a Addressing polysemy in bilingual lexicon extraction from comparable corpora / |c Fišer, Darja ; Ljubešić, Nikola ; Kubelka, Ozren. |
| 246 | 3 | |i Naslov na engleskom: |a Addressing polysemy in bilingual lexicon extraction from comparable corpora | |
| 300 | |f str. | ||
| 520 | |a This paper presents an approach to extract translation equivalents from comparable corpora for polysemous nouns. As opposed to the standard approaches that build a single context vector for all occurrences of a given headword, we first disambiguate the headword with third-party sense taggers and then build a separate context vector for each sense of the headword. Since state-of-the- art word sense disambiguation tools are still far from perfect, we also tried to improve the results by combining the sense assignments provided by two different sense taggers. Evaluation of the results shows that we outperform the baseline (0.473) in all the settings we experimented with, even when using only one sense tagger, and that the best-performing results are indeed obtained by taking into account the intersection of both sense taggers (0.720). | ||
| 536 | |a Projekt MZOS |f 130-1301679-1380 | ||
| 536 | |a Projekt MZOS |f FP7-248347 | ||
| 546 | |a ENG | ||
| 690 | |a 5.04 | ||
| 693 | |a bilingual lexicon extraction, comparable corpora, polysemy |l hrv |2 crosbi | ||
| 693 | |a bilingual lexicon extraction, comparable corpora, polysemy |l eng |2 crosbi | ||
| 700 | 1 | |a Kubelka, Ozren |4 aut | |
| 700 | 1 | |9 445 |a Ljubešić, Nikola, |c informatičar |4 aut | |
| 773 | 0 | |a Eight International Conference on Language Resources and Evaluation (LREC'12) (21-27.05.2012. ; Istanbul, Turska) |t Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC'12) |d Istanbul : 2012 |n Nicoletta Calzolari et al. | |
| 856 | |u http://www.lrec-conf.org/proceedings/lrec2012/index.html | ||
| 942 | |c RZB |u 2 |v Recenzija |z Znanstveni - Predavanje - CijeliRad |t 1.08 | ||
| 999 | |c 318225 |d 318223 | ||