Meta learning for natural language processing: A survey
Deep learning has been the mainstream technique in natural language processing (NLP)
area. However, the techniques require many labeled data and are less generalizable across …
area. However, the techniques require many labeled data and are less generalizable across …
Meta-learning a cross-lingual manifold for semantic parsing
T Sherborne, M Lapata - Transactions of the Association for …, 2023 - direct.mit.edu
Localizing a semantic parser to support new languages requires effective cross-lingual
generalization. Recent work has found success with machine-translation or zero-shot …
generalization. Recent work has found success with machine-translation or zero-shot …
Identifying the correlation between language distance and cross-lingual transfer in a multilingual representation space
F Philippy, S Guo, S Haddadan - arXiv preprint arXiv:2305.02151, 2023 - arxiv.org
Prior research has investigated the impact of various linguistic features on cross-lingual
transfer performance. In this study, we investigate the manner in which this effect can be …
transfer performance. In this study, we investigate the manner in which this effect can be …
Curriculum meta-learning for zero-shot cross-lingual transfer
T Doan, B Le - Knowledge-Based Systems, 2024 - Elsevier
Learning with small data is the challenge facing low-resource domains with insufficient data
to perform the target tasks. Among the state-of-the-art approaches in deep learning and …
to perform the target tasks. Among the state-of-the-art approaches in deep learning and …
Probabilistic Wind Power Forecasting with Limited Data Based on Efficient Parameter Updating Rules
In this paper, we propose a meta-optimizer-based approach for probabilistic wind power
forecasting (WPF) with limited historical data, including offline training and online adaptation …
forecasting (WPF) with limited historical data, including offline training and online adaptation …
Binding oracle: Fine-tuning from stability to binding free energy
The ability to predict changes in binding free energy (▵▵ $ G_ {bind} $) for mutations at
protein-protein interfaces (PPIs) is critical for the understanding genetic diseases and …
protein-protein interfaces (PPIs) is critical for the understanding genetic diseases and …
Emotionally-bridged cross-lingual meta-learning for chinese sexism detection
G Li, P Rajapaksha, R Farahbakhsh… - … Conference on Natural …, 2023 - Springer
Sexism detection remains as an extremely low-resource task for most of the languages
including Chinese. To address this issue, we propose a zero-shot cross-lingual method to …
including Chinese. To address this issue, we propose a zero-shot cross-lingual method to …
Modelling cross-lingual transfer for semantic parsing
TR Sherborne - 2024 - era.ed.ac.uk
Semantic parsing maps natural language utterances to logical form representations of
meaning (eg, lambda calculus or SQL). A semantic parser functions as a human-computer …
meaning (eg, lambda calculus or SQL). A semantic parser functions as a human-computer …