2021
DOI: 10.48550/arxiv.2109.06772
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Improving Zero-shot Cross-lingual Transfer between Closely Related Languages by injecting Character-level Noise

Abstract: Cross-lingual transfer between a high-resource language and its dialects or closely related language varieties should be facilitated by their similarity, but current approaches that operate in the embedding space do not take surface similarity into account. In this work, we present a simple yet effective strategy to improve cross-lingual transfer between closely related varieties by augmenting the data of the high-resource parent language with characterlevel noise to make the model more robust towards spelling… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2022
2022
2022
2022

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 15 publications
0
1
0
Order By: Relevance
“…For example, our sample of target languages does not include any Indo-European languages, such as Germanic or Romance low-resource languages. These languages have been studied before and it has been shown that the best choice for them is transferring from a genealogically related rich-resource language (Aepli and Sennrich, 2021). It might be interesting to see how our proposed measure would compare with other measures in these cases, but this would require a different study design, which we leave for future work.…”
Section: Limitationsmentioning
confidence: 99%
“…For example, our sample of target languages does not include any Indo-European languages, such as Germanic or Romance low-resource languages. These languages have been studied before and it has been shown that the best choice for them is transferring from a genealogically related rich-resource language (Aepli and Sennrich, 2021). It might be interesting to see how our proposed measure would compare with other measures in these cases, but this would require a different study design, which we leave for future work.…”
Section: Limitationsmentioning
confidence: 99%