Search: onr:"swepub:oai:DiVA.org:hj-54861" >
Moses and the Chara...
Moses and the Character-Based Random Babbling Baseline: CoAStaL at AmericasNLP 2021 Shared Task
-
- Bollmann, Marcel (author)
- Jönköping University,Jönköping AI Lab (JAIL),University of Copenhagen, Denmark
-
- Aralikatte, Rahul (author)
- University of Copenhagen, Denmark
-
- Murrieta Bello, Héctor (author)
- University of Copenhagen, Denmark
-
show more...
-
- Hershcovich, Daniel (author)
- University of Copenhagen, Denmark
-
- de Lhoneux, Miryam (author)
- University of Copenhagen, Denmark
-
- Søgaard, Anders (author)
- University of Copenhagen, Denmark
-
show less...
-
(creator_code:org_t)
- Stroudsburg, PA, USA : Association for Computational Linguistics, 2021
- 2021
- English.
-
In: Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas. - Stroudsburg, PA, USA : Association for Computational Linguistics. ; , s. 248-254
- Related links:
-
https://aclanthology...
-
show more...
-
https://www.aclweb.o...
-
https://doi.org/10.1...
-
https://liu.diva-por... (primary) (Raw object)
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
https://urn.kb.se/re...
-
show less...
Abstract
Subject headings
Close
- We evaluated a range of neural machine translation techniques developed specifically for low-resource scenarios. Unsuccessfully. In the end, we submitted two runs: (i) a standard phrase-based model, and (ii) a random babbling baseline using character trigrams. We found that it was surprisingly hard to beat (i), in spite of this model being, in theory, a bad fit for polysynthetic languages; and more interestingly, that (ii) was better than several of the submitted systems, highlighting how difficult low-resource machine translation for polysynthetic languages is.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Språkteknologi (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Language Technology (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences (hsv//eng)
Publication and Content Type
- ref (subject category)
- kon (subject category)
To the university's database