1 |
Abolitionist Networks: Modeling Language Change in Nineteenth-Century Activist Newspapers ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Revisiting the Primacy of English in Zero-shot Cross-lingual Transfer ...
|
|
|
|
Abstract:
Despite their success, large pre-trained multilingual models have not completely alleviated the need for labeled data, which is cumbersome to collect for all target languages. Zero-shot cross-lingual transfer is emerging as a practical solution: pre-trained models later fine-tuned on one transfer language exhibit surprising performance when tested on many target languages. English is the dominant source language for transfer, as reinforced by popular zero-shot benchmarks. However, this default choice has not been systematically vetted. In our study, we compare English against other transfer languages for fine-tuning, on two pre-trained multilingual models (mBERT and mT5) and multiple classification and question answering tasks. We find that other high-resource languages such as German and Russian often transfer more effectively, especially when the set of target languages is diverse or unknown a priori. Unexpectedly, this can be true even when the training sets were automatically translated from English. ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2106.16171 https://dx.doi.org/10.48550/arxiv.2106.16171
|
|
BASE
|
|
Hide details
|
|
4 |
Abolitionist Networks: Modeling Language Change in Nineteenth-Century Activist Newspapers ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Tuiteamos o pongamos un tuit? Investigating the Social Constraints of Loanword Integration in Spanish Social Media ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Tuiteamos o pongamos un tuit? Investigating the Social Constraints of Loanword Integration in Spanish Social Media
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2021)
|
|
BASE
|
|
Show details
|
|
7 |
Will it Unblend?
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2021)
|
|
BASE
|
|
Show details
|
|
8 |
Abolitionist Networks: Modeling Language Change in Nineteenth-Century Activist Newspapers ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
How We Do Things With Words: Analyzing Text as Social and Cultural Data
|
|
|
|
In: Front Artif Intell (2020)
|
|
BASE
|
|
Show details
|
|
14 |
The Referential Reader: A Recurrent Entity Network for Anaphora Resolution ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Discovering Sociolinguistic Associations with Structured Sparsity ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Making "fetch" happen: The influence of social and linguistic context on nonstandard word growth and decline ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Sí o no, què penses? Catalonian Independence and Linguistic Identity on Social Media ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Mind Your POV: Convergence of Articles and Editors Towards Wikipedia's Neutrality Norm ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Making "fetch" happen: The influence of social and linguistic context on nonstandard word growth and decline ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
#anorexia, #anarexia, #anarexyia: Characterizing Online Community Practices with Orthographic Variation ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|