Pregled bibliografske jedinice broj: 1014217
Distant supervision from disparate sources for low-resource part-of-speech tagging
Distant supervision from disparate sources for low-resource part-of-speech tagging // EMNLP 2018: Conference on Empirical Methods in Natural Language Processing: Proceedings / Chang, Kai-Wei (ur.).
Brisel: Association for Computational Linguistics (ACL), 2018. str. 614-620 doi:10.18653/v1/D18-1061 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 1014217 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Distant supervision from disparate sources for
low-resource part-of-speech tagging
Autori
Agić, Željko ; Plank, Barbara
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
EMNLP 2018: Conference on Empirical Methods in Natural Language Processing: Proceedings
/ Chang, Kai-Wei - Brisel : Association for Computational Linguistics (ACL), 2018, 614-620
ISBN
978-1-948087-84-1
Skup
The 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
Mjesto i datum
Bruxelles, Belgija, 31.10.2018. - 04.11.2018
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
low-resource languages ; part-of-speech tagging ; neural networks ; distant supervision
Sažetak
We introduce DSDS: a cross-lingual neural part- of-speech tagger that learns from disparate sources of distant supervision, and realistically scales to hundreds of low- resource languages. The model exploits annotation projection, instance selection, tag dictionaries, morphological lexicons, and distributed representations, all in a uniform framework. The approach is simple, yet surprisingly effective, resulting in a new state of the art without access to any gold annotated data.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo
Citiraj ovu publikaciju:
Časopis indeksira:
- Scopus
