Rethinking embedding coupling in pre-trained language models

Abstract

We re-evaluate the standard practice of sharing weights between input and output embeddings in state-of-the-art pre-trained language models. We show that decoupled embeddings provide increased modeling flexibility, allowing us to significantly improve the efficiency of parameter allocation in the input embedding of multilingual models. By reallocating the input embedding parameters in the Transformer layers, we achieve dramatically better performance on standard natural language understanding tasks with the same number of parameters during fine-tuning. We also show that allocating additional capacity to the output embedding provides benefits to the model that persist through the fine-tuning stage even though the output embedding is discarded after pre-training. Our analysis shows that larger output embeddings prevent the model's last layers from overspecializing to the pre-training task and encourage Transformer representations to be more general and more transferable to other tasks and languages. Harnessing these findings, we are able to train models that achieve strong performance on the XTREME benchmark without increasing the number of parameters at the fine-tuning stage.

References in corpus (14)

• Distilling the Knowledge in a Neural Network
• Language Models are Few-Shot Learners
• Semantics derived automatically from language corpora contain human-like biases
• Scaling Laws for Neural Language Models
• Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
• On the Cross-lingual Transferability of Monolingual Representations
• Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
• GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding
• XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization
• Revisiting Few-sample BERT Fine-tuning
• Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling
• Cross-Lingual Ability of Multilingual BERT: An Empirical Study
• Towards better substitution-based word sense induction
• HULK: An Energy Efficiency Benchmark Platform for Responsible Natural Language Processing

Cited by in corpus (3)

• mT5: A massively multilingual pre-trained text-to-text transformer
• Extracting Sentence Embeddings from Pretrained Transformer Models
• Distilling Large Language Models into Tiny and Effective Students using pQRNN