Challenge: a sandwich transformer pattern is a new approach to multilayer transformers that can be used for different tasks.
Approach: They propose a transformer ordering pattern that reorders sublayers in a sandwich transformer pattern . they generate random transformer models and train them with the language modeling objective .
Outcome: The proposed pattern improves perplexity on multiple word-level and character-level language modeling benchmarks at no cost in parameters, memory, or training time.

Similar Papers

Neural Machine Translation with Reordering Embeddings (P19-1)

Copied to clipboard

Challenge: Existing work exploits the reordering information in neural machine translation . experimental results show that the proposed methods can significantly improve the performance of the transformer translation system.
Approach: They propose a reordering mechanism to learn the re ordering embedding of a word based on contextual information and stack them together with self-attention networks to learn sentence representation for machine translation.
Outcome: The proposed method improves translation performance on English-to-German, NIST Chinese-to English, and WAT Japanese-toEnglish translation tasks.
Hierarchical Transformers Are More Efficient Language Models (2022.findings-naacl)

Copied to clipboard

Challenge: Transformers are impressive but inefficient and costly, which limits their applications and accessibility.
Approach: They first use different ways to downsample and upsamplify activations in Transformers to make them hierarchical.
Outcome: The proposed model outperforms Transformers on the ImageNet32 and enwik8 benchmarks.
Rethinking the Value of Transformer Components (2020.coling-main)

Copied to clipboard

Challenge: Empirical results show that certain components are more important than others . we propose a new training strategy that can improve Transformer models by distinguishing unimportant components .
Approach: They propose a training strategy that distinguishes the unimportant components in training . they compare the impact of individual component (sub-layer) on model performance .
Outcome: The proposed training strategy can improve translation performance by distinguishing unimportant components in training.
How to Dissect a Muppet: The Structure of Transformer Embedding Spaces (2022.tacl-1)

Copied to clipboard

Challenge: Pretrained embeddings based on the Transformer architecture have taken the NLP community by storm . a novel decomposition of Transformer output embeddables is demonstrated .
Approach: They propose to decompose Transformer output embeddings into a sum of vector factors . they show multi-head attentions and feed-forwards are not equally useful in downstream applications .
Outcome: The proposed method outperforms recurrent architectures on a wide variety of tasks.
Subformer: Exploring Weight Sharing for Parameter Efficiency in Generative Transformers (2021.findings-emnlp)

Copied to clipboard

Challenge: Recent improvements in NLP tasks can be attributed to the Transformer model.
Approach: They propose to use parameter-sharing methods to reduce parameter budgets in generative models by using sandwich-style parameter sharing and self-attentive embedding factorization.
Outcome: The proposed model outperforms the current RNN model even with significantly fewer parameters.
Retrofitting Structure-aware Transformer Language Model for End Tasks (2020.emnlp-main)

Copied to clipboard

Challenge: Experimental results show that structure-aware Transformer language model achieves improved perplexity, meanwhile inducing accurate syntactic phrases.
Approach: They propose to exploit syntactic distance to encode phrasal constituency and dependency connection into Transformer language model and leverage it for structure integration.
Outcome: The proposed model achieves significant improvements for both semantic- and syntactic-dependent tasks.
Choose Your Transformer: Improved Transferability Estimation of Transformer Models on Classification Tasks (2024.findings-acl)

Copied to clipboard

Challenge: Existing models for NLP tasks require fine-tuning, but it is computationally infeasible.
Approach: They propose an approach that inexpensively estimates a ranking of the expected performance of a given set of transformer language models for a specific task.
Outcome: The proposed model improves the Pearson correlation coefficient between the true model ranks and the estimate.
Recurrent Positional Embedding for Neural Machine Translation (D19-1)

Copied to clipboard

Challenge: Existing translation systems that use positional embeddings only encode static order dependencies based on discrete numerical information, which may hinder the improvement of translation capacity.
Approach: They propose a recurrent positional embedding approach based on word vectors that are learned by a neural network and integrated into existing multi-head self-attention models.
Outcome: The proposed approach improves translation performance over the state-of-the-art Transformer baseline in English-to-German and NIST Chinese-to English translation tasks.
Assessing Non-autoregressive Alignment in Neural Machine Translation via Word Reordering (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing non-autoregressive neural machine translation models that implicitly model dependencies are sub-optimal in handling word order errors.
Approach: They propose to learn a non-autoregressive language model that can be combined with Viterbi decoding to achieve better reordering performance.
Outcome: The proposed model outperforms state-of-the-art reordering mechanisms under different word permutation settings with a 2-27 BLEU improvement, suggesting high potential for word alignment in NAT.
EFTNAS: Searching for Efficient Language Models in First-Order Weight-Reordered Super-Networks (2024.lrec-main)

Copied to clipboard

Challenge: Depending on the size of transformer-based models, they can be restricted from deployment in resource-constrained environments.
Approach: They propose to combine neural architecture search and network pruning techniques to generate and train weight-sharing super-networks that contain efficient transformer-based models.
Outcome: The proposed model achieves high-performing, high-performance subnetworks on the general language understanding evaluation and the Stanford Question Answering Dataset.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations