How Much Does Attention Actually Attend? Questioning the Importance of Attention in Pretrained Transformers (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Pretrained language models use the attention mechanism to contextualize input inputs . but, we find that it is not as important as thought for pretrained models . |
| Approach: | They propose a probing method that replaces input-dependent attention matrices with constant ones. |
| Outcome: | The proposed method improves performance of pretrained language models without input-dependent attention. |
Similar Papers
Effective Attention Sheds Light On Interpretability (2021.findings-acl)
Copied to clipboard
| Challenge: | Using a subset of the GLUE tasks and BERT, we compare the two attention matrices and show that their interpretations differ. |
| Approach: | They propose to use visualizing effective attention to interpret a transformer's behavior since it is more pertinent to the model output by design. |
| Outcome: | The proposed method is more relevant to the model output by design than visualizing attention weights. |
Attention is Not Only a Weight: Analyzing Transformers with Vector Norms (2020.emnlp-main)
Copied to clipboard
| Challenge: | Attention is a key component of Transformers, which have achieved considerable success in natural language processing. |
| Approach: | They propose to integrate attention weights and the norm of transformed input vectors into a norm-based analysis that incorporates the norm. |
| Outcome: | The proposed analysis shows that attention weights alone determine the output of attention and that reasonable word alignment can be extracted from attention mechanisms of Transformers. |
Quantifying Attention Flow in Transformers (2020.acl-main)
Copied to clipboard
| Challenge: | In the Transformer model, “self-attention” combines information from attended embeddings into the representation of the focal embeddable in the next layer. |
| Approach: | They propose two methods to quantify flow of information through self-attention using attention weights as relative relevance of input tokens. |
| Outcome: | The proposed methods give complementary views on the flow of information and yield higher correlations with importance scores of input tokens. |
Adaptive Attention Span in Transformers (P19-1)
Copied to clipboard
| Challenge: | We extend the maximum context size of a neural network called Transformer to 8k characters. |
| Approach: | They propose a self-attention mechanism that can learn its optimal attention span . this allows for models with longer context and the capability to catch longer dependencies. |
| Outcome: | The proposed model achieves state-of-the-art performance on text8 and enwiki8 using 8k characters with no loss of performance, and maintains control over memory footprint and computational time. |
Telling BERT’s Full Story: from Local Attention to Global Aggregation (2021.eacl-main)
Copied to clipboard
| Challenge: | Recent work discouraging the use of attention distributions for explaining a model’s behaviour suggests that attention distribution can provide insights into local behaviour of attention heads. |
| Approach: | They propose a distinction between local patterns revealed by attention and global patterns that refer back to the input and analyze BERT from both angles. |
| Outcome: | The proposed model can explain local behaviour of attention heads by comparing local and global patterns from both angles. |
Efficient Long-Range Transformers: You Need to Attend More, but Not Necessarily at Every Layer (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Pretrained transformer models have demonstrated remarkable performance across various natural language processing tasks. |
| Approach: | They propose a transformer variant with mixed attention spans that leverages the attention mechanism to capture long- and short-range dependencies in the sequence. |
| Outcome: | The proposed model can achieve competitive performance to models with full attention while reducing computational cost (75%) |
Chain and Causal Attention for Efficient Entity Tracking (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to handle entity tracking require at least log2 (n+1) layers to handle n state changes. |
| Approach: | They propose an efficient enhancement to the standard attention mechanism to handle long-term dependencies with a single layer. |
| Outcome: | The proposed model can handle entity tracking with n state changes with a single layer. |
Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation (2021.emnlp-main)
Copied to clipboard
| Challenge: | a series of experiments show that fine-tuning only the cross-attention parameters is nearly as effective as fine-timing all parameters. |
| Approach: | They conduct experiments to fine-tune a translation model on data where either the source or target language has changed. |
| Outcome: | The proposed model can be trained to several new languages with reduced parameter storage overhead. |
Decoupling the Role of Data, Attention, and Losses in Multimodal Transformers (2021.tacl-1)
Copied to clipboard
| Challenge: | Recent studies suggest multimodal transformer models learn rich visual-linguistic representations. |
| Approach: | They focus on dataset noise and language similarity to their downstream task . they find that models with a multimodal attention mechanism outperform deeper models with modality-specific attention mechanisms. |
| Outcome: | The proposed models outperform models with a multimodal attention mechanism on downstream tasks. |
How Far Does BERT Look At: Distance-based Clustering and Analysis of BERT’s Attention (2020.coling-main)
Copied to clipboard
| Challenge: | Recent work on multi-head attention mechanism shows heuristics and clues in analyzing various aspects of the mechanism. |
| Approach: | They propose to cluster attention heatmaps into significantly different patterns through unsupervised clustering on top of a set of proposed features. |
| Outcome: | The proposed features can explain and calibrate different attention heads in Transformer models. |