Combining Parameter-efficient Modules for Task-level Generalisation
Authors:
- Edoardo Maria PontiEPEdoardo Maria Ponti
- Alessandro SordoniASAlessandro Sordoni
Open Access
- 1 January 2023
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 687-702
Abstract
Edoardo Maria Ponti, Alessandro Sordoni, Yoshua Bengio, Siva Reddy. Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics. 2023.Keywords
This publication has 10 references indexed in Scilit:
- Neural Network Module Decomposition and Recomposition with Superimposed Masks2023
- Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference2021
- MAD-G: Multilingual Adapter Generation for Efficient Cross-Lingual Transfer2021
- CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP2021
- Minimax and Neyman–Pearson Meta-Learning for Outlier Languages2021
- Compositionality Decomposed: How do Neural Networks Generalise?Journal of Artificial Intelligence Research, 2020
- GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding2018
- Long Short-Term MemoryNeural Computation, 1997
- Task Decomposition Through Competition in a Modular Connectionist Architecture: The What and Where Vision TasksCognitive Science, 1991
- Adaptive Mixtures of Local ExpertsNeural Computation, 1991