| Challenge: | Existing frameworks for natural language processing ignore interactions among different heads, which wastes the capacity of the model. |
| Approach: | They propose a model which explicitly models interactions between attention heads through a hierarchical variational distribution. |
| Outcome: | The proposed model outperforms the baseline model on Wikitext-103 and WMT14 EN-DE on language modeling and translation tasks. |
Similar Papers
Multiformer: A Head-Configurable Transformer-Based Model for Direct Speech Translation (2022.naacl-srw)
Copied to clipboard
| Challenge: | Existing approaches to address speech tasks with a self-attention mechanism are expensive and lead to information loss. |
| Approach: | They propose a Transformer-based model which uses different attention mechanisms on each head to bias the self-attention towards the extraction of more diverse token interactions. |
| Outcome: | The proposed model outperforms baseline models by 0.7 BLEU in the speech task. |
Pit One Against Many: Leveraging Attention-head Embeddings for Parameter-efficient Multi-head Attention (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing pre-trained language models have produced performance gains in various tasks but come with large computational requirements. |
| Approach: | They propose an alternative module that uses only a single shared projection matrix and multiple head embeddings (MHE) they demonstrate that MHE attention is substantially more memory efficient compared to alternative attention mechanisms. |
| Outcome: | The proposed model is more memory efficient compared to the current model while achieving high retention ratio on several downstream tasks. |
Shapley Head Pruning: Identifying and Removing Interference in Multilingual Transformers (2023.eacl-main)
Copied to clipboard
| Challenge: | Multilingual transformer-based models demonstrate remarkable zero and few-shot transfer across languages by learning and reusing language-agnostic features. |
| Approach: | They propose to prune attention heads from a fixed model to reduce interference as a model acquires more languages. |
| Outcome: | The proposed model can reduce interference by pruning language-specific attention heads. |
Mixed Multi-Head Self-Attention for Neural Machine Translation (D19-56)
Copied to clipboard
| Challenge: | Recent advances in neural machine translation have been made in the field of multi-head self-attention and there is no explicit mechanism to ensure that different attention heads capture different features. |
| Approach: | They propose a novel multi-head self-attention model which models not only global and local attention but also forward and backward attention in different attention heads. |
| Outcome: | The proposed model improves on WAT17 English-Japanese and IWSLT14 German-English translation tasks without increasing the number of parameters. |
Contributions of Transformer Attention Heads in Multi- and Cross-lingual Tasks (2021.acl-long)
Copied to clipboard
| Challenge: | Prior research has found that only a few attention heads are important in each mono-lingual NLP task and pruning the remaining heads leads to comparable or improved performance of the model. |
| Approach: | They examine the relative importance of attention heads in Transformer-based models to aid their interpretability in cross-lingual and multi-lingual tasks. |
| Outcome: | The proposed model performs better with the remaining heads pruned than with the other models, the authors show . |
Attention over Heads: A Multi-Hop Attention for Neural Machine Translation (P19-2)
Copied to clipboard
| Challenge: | Existing multihop attentions for machine comprehension are recurrent and hierarchical . a proposed multi-hop attention for the Transformer refines the attention for an output symbol many times . |
| Approach: | They propose a multi-hop attention for the Transformer which integrates attentions from each head. |
| Outcome: | The proposed model outperforms the baseline Transformer in terms of translation accuracy and speed. |
Finding the Pillars of Strength for Multi-Head Attention (2023.acl-long)
Copied to clipboard
| Challenge: | Recent studies have revealed some issues of Multi-Head Attention (MHA) e.g., redundancy and over-parameterization. |
| Approach: | They propose to train attention heads with a self-supervised group constraint to focus on an essential but distinctive feature subset. |
| Outcome: | The proposed method achieves significant performance gains on three well-established tasks while significantly compressing parameters. |
HIT - A Hierarchically Fused Deep Attention Network for Robust Code-mixed Language Representation (2021.findings-acl)
Copied to clipboard
| Challenge: | linguistics and morphology of resource-short code-mixed texts remain a key challenge in text processing. |
| Approach: | They propose a hierarchical transformer-based framework that captures the semantic relationship among words and hierarchically learns sentencelevel semantics using a fused attention mechanism. |
| Outcome: | The proposed framework improves on one European and five Indic languages on four NLP tasks on eleven datasets. |
Incorporating Residual and Normalization Layers into Analysis of Masked Language Models (2021.emnlp-main)
Copied to clipboard
| Challenge: | Transformer architecture is composed of multi-head attention, which has been extensively analyzed. |
| Approach: | They extended the scope of the analysis of Transformers from solely the attention patterns to the whole attention block, i.e., multi-head attention, residual connection, and layer normalization. |
| Outcome: | The proposed method incorporates the whole attention block, i.e., multi-head attention, residual connection, and layer normalization into the analysis. |
Mitigating Attention Localization in Small Scale: Self-Attention Refinement via One-step Belief Propagation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a new framework for self-attention models is proposed to address this problem . it injects *multi-hop* relationships into the attention graph, allowing for better performance . |
| Approach: | They propose a framework that injects *multi-hop* relationships through a belief propagation process. |
| Outcome: | The proposed framework helps prevent entropy collapse in deeper layers and maintains GTD at task-appropriate levels. |