Search: onr:"swepub:oai:DiVA.org:uu-365768" >
Parameter sharing b...
Parameter sharing between dependency parsers for related languages
-
- de Lhoneux, Miryam, 1990- (author)
- Uppsala universitet,Institutionen för lingvistik och filologi,Computational Linguistics
-
- Bjerva, Johannes (author)
- University of Copenhagen,Univ Copenhagen, Dept Comp Sci, Copenhagen, Denmark.
-
- Augenstein, Isabelle (author)
- University of Copenhagen,Univ Copenhagen, Dept Comp Sci, Copenhagen, Denmark.
-
show more...
-
- Søgaard, Anders (author)
- University of Copenhagen,Univ Copenhagen, Dept Comp Sci, Copenhagen, Denmark.
-
show less...
-
(creator_code:org_t)
- Brussels : Association for Computational Linguistics, 2018
- 2018
- English.
-
In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. - Brussels : Association for Computational Linguistics. - 9781948087841 ; , s. 4992-4997
- Related links:
-
http://aclweb.org/an...
-
show more...
-
https://urn.kb.se/re...
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- Previous work has suggested that parameter sharing between transition-based neural dependency parsers for related languages can lead to better performance, but there is no consensus on what parameters to share. We present an evaluation of 27 different parameter sharing strategies across 10 languages, representing five pairs of related languages, each pair from a different language family. We find that sharing transition classifier parameters always helps, whereas the usefulness of sharing word and/or character LSTM parameters varies. Based on this result, we propose an architecture where the transition classifier is shared, and the sharing of word and character parameters is controlled by a parameter that can be tuned on validation data. This model is linguistically motivated and obtains significant improvements over a mono-lingually trained baseline. We also find that sharing transition classifier parameters helps when training a parser on unrelated language pairs, but we find that, in the case of unrelated languages, sharing too many parameters does not help.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Språkteknologi (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Language Technology (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Keyword
- parameter sharing
- dependency parsing
- multilingual parsing
- Datorlingvistik
- Computational Linguistics
Publication and Content Type
- ref (subject category)
- kon (subject category)
Find in a library
To the university's database