DE eng

Search in the Catalogues and Directories

Hits 1 – 8 of 8

1
Minimax and Neyman–Pearson Meta-Learning for Outlier Languages ...
BASE
Show details
2
Minimax and Neyman–Pearson Meta-Learning for Outlier Languages ...
Abstract: Read paper: https://www.aclanthology.org/2021.findings-acl.106 Abstract: Model-agnostic meta-learning (MAML) has been recently put forth as a strategy to learn resource-poor languages in a sample-efficient fashion. Nevertheless, the properties of these languages are often not well represented by those available during training. Hence, we argue that the i.i.d. assumption ingrained in MAML makes it ill-suited for cross-lingual NLP. In fact, under a decision-theoretic framework, MAML can be interpreted as minimising the expected risk across training languages (with a uniform prior), which is known as Bayes criterion. To increase its robustness to outlier languages, we create two variants of MAML based on alternative criteria: Minimax MAML reduces the maximum risk across languages, while Neyman–Pearson MAML constrains the risk in each language to a maximum threshold. Both criteria constitute fully differentiable two-player games. In light of this, we propose a new adaptive optimiser solving for a local ...
Keyword: Computational Linguistics; Condensed Matter Physics; Deep Learning; Electromagnetism; FOS Physical sciences; Information and Knowledge Engineering; Neural Network; Semantics
URL: https://underline.io/lecture/26197-minimax-and-neyman-pearson-meta-learning-for-outlier-languages
https://dx.doi.org/10.48448/1h13-vc36
BASE
Hide details
3
Minimax and Neyman–Pearson Meta-Learning for Outlier Languages ...
BASE
Show details
4
Visually Grounded Reasoning across Languages and Cultures ...
BASE
Show details
5
Visually Grounded Reasoning across Languages and Cultures ...
BASE
Show details
6
LexFit: Lexical Fine-Tuning of Pretrained Language Models ...
BASE
Show details
7
Verb Knowledge Injection for Multilingual Event Processing ...
BASE
Show details
8
Multi-SimLex: A Large-Scale Evaluation of Multilingual and Cross-Lingual Lexical Semantic Similarity ...
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
8
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern