Inducing Systematicity in Transformers by Attending to Structurally Quantized Embeddings (2024.acl-long)
Copied to clipboard
| Challenge: | Empirically, we show SQ-Transformer achieves stronger compositional generalization than the vanilla Transformer on low-complexity datasets. |
| Approach: | They propose a Transformer that explicitly encourages systematicity in the embeddings and attention layers even with low-complexity data. |
| Outcome: | Empirically, the proposed model achieves stronger compositional generalization than the vanilla Transformer on low-complexity datasets. |
Similar Papers
Understanding and Overcoming the Challenges of Efficient Transformer Quantization (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in transformer quantization have shown remarkable improvement in many Natural Language Processing tasks and beyond. |
| Approach: | They propose a novel quantization scheme for transformers that can be quantized to ultra-low bit-widths, leading to significant memory savings with a minimum accuracy loss. |
| Outcome: | The proposed methods achieve state-of-the-art results on the GLUE benchmark using BERT, while preserving memory and accuracy. |
Systematicity Emerges in Transformers when Abstract Grammatical Roles Guide Attention (2022.naacl-srw)
Copied to clipboard
| Challenge: | Existing systems that use transformers lack systematicity, but they are inferior to human learners in sample efficiency and difficult generalization problems. |
| Approach: | They propose to modify a transformer so that it controls attention distributions and fills in the gaps. |
| Outcome: | The proposed model shows that the performance of natural language processing systems is improved when abstract role labels are assigned to the input stream and provided to the role stream. |
Structural Guidance for Transformer Language Models (2021.acl-long)
Copied to clipboard
| Challenge: | Pre-trained Transformer language models have proven remarkably successful in learning generic transferable linguistic representations without resorting to data intensive pre-training. |
| Approach: | They propose to combine a generative parsing and a structural scaffolding idea to guide the model's representation via additional structure loss that separates the incremental constituency parse. |
| Outcome: | The proposed models achieve impressive perplexity results on language modelling datasets, perform well on grammatical judgments, and provide useful linguistic representations that benefit a wide range of downstream tasks. |
Exploring Quantization for Efficient Pre-Training of Transformer Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Quantization has proven to be effective after pre-training and during fine-tuning, but its effects on pre-trainer performance have remained unexplored. |
| Approach: | They propose a linear quantization strategy to be applied during the pre-training of Transformers to improve model efficiency and stability. |
| Outcome: | The proposed method improves model efficiency, stability, and performance while maintaining language modeling ability. |
Inducing Transformer’s Compositional Generalization Ability via Auxiliary Sequence Prediction Tasks (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing neural models lack systematic compositionality in learning symbolic structures . existing models lack this ability in learning symbols, despite being able to understand complex structures. |
| Approach: | They propose to use auxiliary sequence prediction tasks to train a Transformer model to understand compositional symbolic structures of input data. |
| Outcome: | The proposed model improves on the SCAN compositionality challenge, with only 418 (5%) training instances, and achieves 97.8% accuracy on the MCD1 split. |
Quantifying Compositionality of Classic and State-of-the-Art Embeddings (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Static word embeddings make strong claims about compositionality, but the SOTA generative models go too far in the other direction. |
| Approach: | a new study evaluates the compositionality of word embeddings by canonical correlation analysis . strong compositional signals are observed in later training stages across data modalities . |
| Outcome: | a new evaluation of compositional models shows that they exploit access meanings when justified . strong compositional signals are observed in later training stages and in deeper layers of the transformer-based model before a decline at the top layer. |
Grokking of Hierarchical Structure in Vanilla Transformers (2023.acl-short)
Copied to clipboard
| Challenge: | a recent study has shown that neural sequence models like transformers can generalize hierarchically when training for extended periods. |
| Approach: | They show that transformers can learn to generalize hierarchically after long training periods . they call this phenomenon structural grokking, which exhibits inverted U-shaped scaling in model depth . |
| Outcome: | The proposed model generalizes better than both very deep and very shallow models on multiple datasets. |
On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in Transformers (2021.findings-acl)
Copied to clipboard
Tianchu Ji, Shraddhan Jain, Michael Ferdman, Peter Milder, H. Andrew Schwartz, Niranjan Balasubramanian
| Challenge: | Recent work shows that attention can be pruned to zeros with minimal loss in accuracy. |
| Approach: | They propose a pruning technique which quantizes attention to a 3-bit format without retraining . they find that 80% of attention values can be pruned to zeros with minimal loss in accuracy . |
| Outcome: | The proposed approach produces only a few unique attention values with minimal loss in accuracy. |
Beyond Position: the emergence of wavelet-like properties in Transformers (2025.acl-long)
Copied to clipboard
| Challenge: | Despite its widespread adoption, theoretical limitations in positional encodings are resolved by developing emergent, wavelet-like processing strategies. |
| Approach: | They propose to use Rotary Position Embeddings to develop emergent, wavelet-like properties that compensate for the positional encoding’s theoretical limitations. |
| Outcome: | The attention heads evolve to implement multi-resolution processing analogous to wavelet transforms. |
The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies show that basic configurations can improve the performance of neural networks on systematic generalization. |
| Approach: | They propose to revisit basic configurations to improve the performance of Transformers on systematic generalization by revisiting scaling of embeddings, early stopping, relative positional embeddment, and Universal Transformer variants. |
| Outcome: | The proposed models improve accuracy from 50% to 85% on the PCFG productivity split and from 35% to 81% on COGS. |