| Challenge: | Existing subnetworks of one-layer randomly weighted neural networks can achieve impressive performance without changing initializations. |
| Approach: | They find subnetworks within one-layer randomly weighted neural networks that can achieve impressive performance without ever modifying the initializations. |
| Outcome: | The proposed subnetworks match 98%/92% of the performance of a trained Transformersmall/base on IWSLT14/WMT14. |
Similar Papers
Reservoir Transformers (2021.acl-long)
Copied to clipboard
| Challenge: | Using random initialization, we show that some transformers obtain impressive performance even when some of the layers are frozen. |
| Approach: | They propose to freeze transformer layers and use them to improve performance . they find that the transformers obtain impressive performance even when some of the layers are randomly initialized and never updated. |
| Outcome: | The proposed model improves on translation and language modelling tasks even when some layers are frozen. |
On the Sub-layer Functionalities of Transformer Decoder (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing efforts to interpret the encoder of Transformer-based encoder-decoder architectures for neural machine translation have focused on assessing the encoded representations or interpreting the multi-head self-attentions. |
| Approach: | They propose to use Transformer-based encoder-decoder architectures to analyze how information is propagated through each module of each decoder layer. |
| Outcome: | The proposed model can be dropped with minimal loss of performance on three translation datasets and can be used to train and inference faster. |
Understanding and Improving Hidden Representations for Neural Machine Translation (N19-1)
Copied to clipboard
| Challenge: | Existing studies have explored some methods for understanding hidden representations, but they have not sought to improve the translation quality rationally according to their understanding. |
| Approach: | They propose to construct a sequence of nested relative tasks and measure the feature generalization ability of the learned hidden representation over these tasks. |
| Outcome: | The proposed methods achieve consistent improvements (up to +1.3 BLEU) on two widely-used datasets. |
Do Transformers Parse while Predicting the Masked Word? (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies show that pre-trained language models encode linguistic structures like parse trees while being trained unsupervised. |
| Approach: | They propose to train pre-trained language models to encode linguistic structures like parse trees while unsupervised. |
| Outcome: | The proposed model performs optimally for masked language modeling loss on the English PCFG. |
Learning Deep Transformer Models for Machine Translation (P19-1)
Copied to clipboard
| Challenge: | Neural machine translation models have advanced the previous state-of-the-art by learning mappings between sequences via neural networks and attention mechanisms. |
| Approach: | They propose to use layer normalization to pass the combination of previous layers to the next layer to improve the model. |
| Outcome: | The proposed model outperforms the shallow Transformer-Big/Base baseline model on English-German and Chinese-English tasks by 0.4-2.4 BLEU points. |
Analyzing the Inner Workings of Transformers in Compositional Generalization (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing studies on compositional generalization abilities of neural models have focused on benchmarks, but the results do not reflect the underlying competence of the model. |
| Approach: | They propose to find an existing subnetwork that contributes to the generalization performance and perform causal analyses on how the model utilizes syntactic features. |
| Outcome: | The proposed model relies on syntactic features but the subnetwork with better generalization performance relies mainly on a non-compositional algorithm . |
Improving Lexical Choice in Neural Machine Translation (N18-1)
Copied to clipboard
| Challenge: | False positives: the output layer rewards frequent words disproportionately, we argue . Falsibles: a model that learns word representations in continuous space tends to translate rare words . |
| Approach: | They propose to fix the norms of both vectors to a constant value and integrate a lexical module which is jointly trained with the rest of the model. |
| Outcome: | The proposed approach achieves improvements of up to +4.3 BLEU surpassing phrase-based translation in nearly all settings. |
Improving Transformer Models by Reordering their Sublayers (2020.acl-main)
Copied to clipboard
| 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. |
Disentangling Representations of Text by Masking Transformers (2021.emnlp-main)
Copied to clipboard
| Challenge: | Large pretrained models such as BERT encode a range of features into monolithic vectors, providing strong predictive accuracy across downstream tasks. |
| Approach: | They explore whether it is possible to learn disentangled representations by identifying existing subnetworks within pretrained models that encode distinct, complementary aspects. |
| Outcome: | The proposed method disentangles sentiment from genre in movie reviews, toxicity from dialect in Tweets, and syntax from semantics. |
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. |