1 |
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. However, current approaches that operate in the embedding space do not take surface similarity into account. This work presents a simple yet effective strategy to imrove cross-lingual transfer between closely related varieties. We propose to augment the data of the high-resource source language with character-level noise to make the model more robust towards spelling variations. Our strategy shows consistent improvements over several languages and tasks: Zero-shot transfer of POS tagging and topic identification between language varieties from the Finnic, West and North Germanic, and Western Romance language branches. Our work provides evidence for the usefulness of simple surface-level noise in improving transfer between language varieties. ... : ACL 2022 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences; I.2.7
|
|
URL: https://dx.doi.org/10.48550/arxiv.2109.06772 https://arxiv.org/abs/2109.06772
|
|
BASE
|
|
Hide details
|
|
8 |
On Biasing Transformer Attention Towards Monotonicity
|
|
|
|
In: Rios, Annette; Amrhein, Chantal; Aepli, Noëmi; Sennrich, Rico (2021). On Biasing Transformer Attention Towards Monotonicity. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Online, 6 June 2021 - 11 June 2021. Association for Computational Linguistics, 4474-4488. (2021)
|
|
BASE
|
|
Show details
|
|
12 |
Approaching SMM4H with Merged Models and Multi-task Learning
|
|
|
|
In: Ellendorff, Tilia; Furrer, Lenz; Colic, Nicola; Aepli, Noëmi; Rinaldi, Fabio (2019). Approaching SMM4H with Merged Models and Multi-task Learning. In: Proceedings of the 4th Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task, Florence, Italy, 2 August 2019 - 2 August 2019, 58-61. (2019)
|
|
BASE
|
|
Show details
|
|
13 |
Findings of the VarDial Evaluation Campaign 2017
|
|
|
|
In: Proceedings of the Fourth Workshop on NLP for Similar Languages, Varieties and Dialects (2017)
|
|
BASE
|
|
Show details
|
|
14 |
Crowdsourcing Swiss Dialect Transcriptions for Assessing Factors in Writing Variations ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Building a Parallel Corpus on the World's Oldest Banking Magazine
|
|
|
|
In: Volk, Martin; Amrhein, Chantal; Aepli, Noëmi; Müller, Mathias; Ströbel, Phillip (2016). Building a Parallel Corpus on the World's Oldest Banking Magazine. In: KONVENS, Bochum, 19 September 2016 - 21 September 2016. (2016)
|
|
BASE
|
|
Show details
|
|
16 |
Crowdsourcing Swiss Dialect Transcriptions for Assessing Factors in Writing Variations
|
|
|
|
In: Clematide, Simon; Frick, Karina; Aepli, Noëmi; Goldman, Jean-Philippe (2016). Crowdsourcing Swiss Dialect Transcriptions for Assessing Factors in Writing Variations. In: Proceedings of the 13th Conference on Natural Language Processing (KONVENS) Bochum, Germany September 19–21, 2016, Bochum, 19 September 2016 - 21 September 2016, 62-67. (2016)
|
|
BASE
|
|
Show details
|
|
17 |
A Resource for Natural Language Processing of Swiss German Dialects ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
A Resource for Natural Language Processing of Swiss German Dialects
|
|
|
|
In: Hollenstein, Nora; Aepli, Noëmi (2015). A Resource for Natural Language Processing of Swiss German Dialects. In: International Conference of the German Society for Computational Linguistics and Language Technology (GSCL), Duisburg-Essen, 30 September 2015 - 2 October 2015. (2015)
|
|
BASE
|
|
Show details
|
|
19 |
Compilation of a Swiss German Dialect Corpus and its Application to PoS Tagging ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Part-of-Speech Tag Disambiguation by Cross-Linguistic Majority Vote ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|