DE eng

Search in the Catalogues and Directories

Hits 1 – 5 of 5

1
Constrained Density Matching and Modeling for Cross-lingual Alignment of Contextualized Representations ...
Zhao, Wei; Eger, Steffen. - : arXiv, 2022
Abstract: Multilingual representations pre-trained with monolingual data exhibit considerably unequal task performances across languages. Previous studies address this challenge with resource-intensive contextualized alignment, which assumes the availability of large parallel data, thereby leaving under-represented language communities behind. In this work, we attribute the data hungriness of previous alignment techniques to two limitations: (i) the inability to sufficiently leverage data and (ii) these techniques are not trained properly. To address these issues, we introduce supervised and unsupervised density-based approaches named Real-NVP and GAN-Real-NVP, driven by Normalizing Flow, to perform alignment, both dissecting the alignment of multilingual subspaces into density matching and density modeling. We complement these approaches with our validation criteria in order to guide the training process. Our experiments encompass 16 alignments, including our approaches, evaluated across 6 language pairs, synthetic ...
Keyword: Computation and Language cs.CL; FOS Computer and information sciences
URL: https://dx.doi.org/10.48550/arxiv.2201.13429
https://arxiv.org/abs/2201.13429
BASE
Hide details
2
Towards Explainable Evaluation Metrics for Natural Language Generation ...
BASE
Show details
3
Global Explainability of BERT-Based Evaluation Metrics by Disentangling along Linguistic Factors ...
BASE
Show details
4
Inducing Language-Agnostic Multilingual Representations ...
BASE
Show details
5
On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluation ...
BASE
Show details

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
5
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern