Aston Zhang, Alvin Chan, Yi Tay, Jie Fu, Shuohang Wang, Shuai Zhang, Huajie Shao, Shuochao Yao, Roy Ka-Wei Lee
| Challenge: | a dedicated study on orthogonality constraints for transformers has been lacking . plug-and-play constraints increase the BLEU of transformers . |
| Approach: | They propose to use plug-and-play constraints to encourage matrices to be orthogonal for numerical stability. |
| Outcome: | The proposed constraint increases the BLEU on the large-scale WMT’16 EnDe benchmark by a factor of 28.4 to 29.6. |
Similar Papers
Can Transformers Learn n-gram Language Models? (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing work has tested transformers' ability to represent formal languages, but language models are not classifiers of strings but rather distributions over them. |
| Approach: | They relate transformers' ability to learn random n-gram language models to ngram language model (LM) they find add- smoothing outperforms transformers on the former, while transformers perform better on the latter . |
| Outcome: | The proposed models outperform classical methods designed to learn n-gram LMs, while transformers perform better on the latter. |
Unravelling the Logic: Investigating the Generalisation of Transformers in Numerical Satisfiability Problems (2025.acl-long)
Copied to clipboard
| Challenge: | Transformer models exhibit minimal scale and noise invariance, along with limited vocabulary and number invariancy. |
| Approach: | They probe the generalisation prowess of Transformer models with respect to the hitherto unexplored domain of numerical satisfiability problems. |
| Outcome: | The proposed models exhibit minimal scale and noise invariance, along with limited vocabulary and number invariancy. |
Transformers in the loop: Polarity in neural models of language (2022.acl-long)
Copied to clipboard
| Challenge: | Recent Transformer-based language representation models (LRMs) show impressive results on practical text analysis tasks, but do they have access to complex linguistic notions? |
| Approach: | They propose to use polarity as a case study to compare metrics derived from language models to human judgments obtained in psycholinguistic experiments. |
| Outcome: | The proposed model is more accurate than linguistic theory predictions for polarity, and allows us to use language models to discover new insights into natural language grammar beyond existing linguistic theories. |
Transformer-specific Interpretability (2024.eacl-tutorials)
Copied to clipboard
| Challenge: | Transformers are dominant play-ers in various scientific fields, but their inner workings remain opaque. |
| Approach: | This tutorial presents a trending approach to interpreting Transformers . it uses specific features of the Transformer architecture to quantify context- mixing interactions . |
| Outcome: | This tutorial aims to show how a new trending approach can be applied to Transformer-based models. |
Revisiting Offline Compression: Going Beyond Factorization-based Methods for Transformer Language Models (2023.findings-eacl)
Copied to clipboard
| Challenge: | Recent transformer language models achieve outstanding results on many downstream tasks, but their enormous size often makes them impractical on memory-constrained devices. |
| Approach: | They propose an offline compression approach that reduces the complexity of the model by enabling collaboration between modules. |
| Outcome: | The proposed approach outperforms commonly used factorization-based offline compression methods on various NLP tasks. |
Sneaking Syntax into Transformer Language Models with Tree Regularization (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for incorporating syntactic inductive biases into transformers are limited . we introduce auxiliary loss function that converts bracketing decisions into differentiable orthogonality constraints on vector hidden states. |
| Approach: | They propose to introduce syntactic inductive biases into transformer circuits through a structured regularizer. |
| Outcome: | The proposed approach could unlock more robust and data-efficient learning in transformer language models . it integrates seamlessly with the standard LM objective, requiring no architectural changes. |
Towards Incremental Transformers: An Empirical Analysis of Transformer Models for Incremental NLU (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent work attempts to apply incremental processing to NLUs but this is computationally expensive and does not scale efficiently for long sequences. |
| Approach: | They propose to apply Transformers incrementally via restart-incrementality by repeatedly feeding, to an unchanged model, increasingly longer input prefixes to produce partial outputs. |
| Outcome: | The proposed model has better incremental performance and faster inference speed compared to the standard Transformer and LT with restart-incrementality, at the cost of part of the non-incremental quality. |
Optimizing Transformer for Low-Resource Neural Machine Translation (2020.coling-main)
Copied to clipboard
| Challenge: | Language pairs with limited amounts of parallel data remain a challenge for neural machine translation. |
| Approach: | They propose to optimize a Transformer model for low-resource conditions to improve translation quality by 7.3 BLEU points compared to the default settings. |
| Outcome: | The proposed model improves translation quality up to 7.3 BLEU points compared to the default settings on the IWSLT14 training data compared with the Transformer model. |
Understanding the Difficulty of Training Transformers (2020.emnlp-main)
Copied to clipboard
| Challenge: | Admin (Adaptive model initialization) is more stable, converges faster, and leads to better performance. |
| Approach: | They propose a model initialization algorithm to stabilize early training and unleash its full potential in the late stage. |
| Outcome: | The proposed model initialization method stabilizes early training and unleashes full potential in late stage. |
Working Memory Constraints Scaffold Learning in Transformers under Data Scarcity (2026.findings-acl)
Copied to clipboard
| Challenge: | a recent study has shown that human-like working memory constraints can be integrated into the Transformer architecture . our model incorporates fixed-width windows and temporal decay based attention mechanisms . |
| Approach: | They propose to integrate working memory constraints into the Transformer architecture . they use fixed-width windows and temporal decay-based attention mechanisms . |
| Outcome: | The proposed models show that they can learn better when training data is scarce . the findings suggest that such constraints may serve as a beneficial bias guiding models towards more robust representations . |