Papers with multi-head attention
Repulsive Attention: Rethinking Multi-head Attention as Bayesian Inference (2020.emnlp-main)
Copied to clipboard
Bang An, Jie Lyu, Zhenyi Wang, Chunyuan Li, Changwei Hu, Fei Tan, Ruiyi Zhang, Yifan Hu, Changyou Chen
| Challenge: | Existing studies show that multi-head attention is an effective module in deep neural networks, but there are no explicit mechanisms guaranteeing this property. |
| Approach: | They propose a non-parametric approach that explicitly improves the repulsiveness in multi-head attention and consequently strengthens model’s expressiveness. |
| Outcome: | The proposed approach improves the repulsiveness in multi-head attention and strengthens model’s expressiveness. |
Long-range Sequence Modeling with Predictable Sparse Attention (2022.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to capture global context dependencies in sequence modeling suffer from quadratic complexity in time and memory usage. |
| Approach: | They propose an efficient Transformer architecture for fast long-range sequence modeling with a sparse attention matrix and a hidden state cross module. |
| Outcome: | The proposed architecture outperforms the standard multi-head attention and its variants in various long-sequence tasks with low computational costs. |
Multiˆ2OIE: Multilingual Open Information Extraction Based on Multi-Head Attention with BERT (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing open IE systems were based on handcrafted features or fine-grained rules. |
| Approach: | They propose a multi-head argument extraction method using multi-lingual BERT . they use a query, key, and value setting inspired by the Multimodal Transformer . |
| Outcome: | The proposed method outperforms existing sequence-labeling systems on two benchmark datasets and on two languages without training data. |
EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained language models have shown remarkable results on various NLP tasks. |
| Approach: | They propose to improve the feed-forward network (FFN) in BERT with a higher computational cost than improving the multi-head attention (MHA). |
| Outcome: | The proposed model is 6.9 smaller and 4.4 faster than BERTBASE and has competitive performances on GLUE and SQuAD Benchmarks. |
Recover-LoRA: Data-Free Accuracy Recovery of Degraded Language Models via Low-Rank Adaptation (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Inference optimizations such as quantization, pruning, format and datatype conversion, model export, and serialization can lead to functional degradations in language model task performance. |
| Approach: | They propose a lightweight and dataset-agnostic method to recover model accuracies from quantization, pruning, format and datatype conversion, model export, and serialization errors. |
| Outcome: | The proposed method recovers model accuracies by 5-17% on MHA and GQA models. |
Cross-Media Keyphrase Prediction: A Unified Framework with Multi-Modality Multi-Head Attention and Image Wordings (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies focus on text modeling, ignoring the rich features embedded in the matching images. |
| Approach: | They propose a novel multi-modal multi-head attention model to capture cross-media interactions and image wordings to bridge the two modalities. |
| Outcome: | The proposed model outperforms the current state of the art based on text modeling and image matching . |
Multi-Domain Dialogue State Tracking with Disentangled Domain-Slot Attention (2023.findings-acl)
Copied to clipboard
| Challenge: | Multi-domain dialogue state tracking is a challenge for task-oriented dialogue systems . domains and slots are aggregated into a single query to generate domain-slot specific representations . |
| Approach: | They propose to disentangle domain-slot attention for multi-domain dialogue state tracking by separating query about domains and slots from the attention component. |
| Outcome: | The proposed approach outperforms the standard multi-head attention with aggregated domain-slot query. |
Information Aggregation for Multi-Head Attention with Routing-by-Agreement (N19-1)
Copied to clipboard
| Challenge: | Existing studies focus on extracting informative or distinct partial-representations from different subspaces, while few studies have paid attention to the aggregation of the extracted partial-Representations. |
| Approach: | They propose to use a routing-by-agreement algorithm to improve multi-head attention by iteratively updating the proportion of how much a part should be assigned to a whole based on agreement between parts and wholes. |
| Outcome: | The proposed algorithm improves the information aggregation for multi-head attention over the standard linear transformation on linguistic probing and machine translation tasks. |
Incorporating Circumstances into Narrative Event Prediction (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies focus on mining the inter-events relationships while ignoring how the events happened. |
| Approach: | They propose to incorporate event circumstances into the narrative event prediction by combining two multi-head attention modules and regularizing attention weights. |
| Outcome: | The proposed model outperforms baseline models by 12.2%. |
LongHeads: Multi-Head Attention is Secretly a Long Context Processor (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models struggle to process lengthy inputs due to limited length generalization and attention’s quadratic computational demands. |
| Approach: | They propose a training-free framework that allows each head to attend to important context chunks instead of allowing each head a full sentence . |
| Outcome: | The proposed framework unlocks multi-head attention's untapped potential by allowing each head to attend to important context chunks instead of the full sentence. |
Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policy (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for simultaneous machine translation require multiple models for different latency levels, resulting in large computational costs. |
| Approach: | They propose a universal SiMT model with Mixture-of-Experts Wait-k Policy to achieve the best translation quality under arbitrary latency with only one model. |
| Outcome: | The proposed model outperforms all the strong baselines under different latency levels including the state-of-the-art adaptive policy. |
Incorporating Zoning Information into Argument Mining from Biomedical Literature (2022.lrec-1)
Copied to clipboard
| Challenge: | Argumentative zoning is a text zonation scheme that is used to segment text into zones that serve distinct functions. |
| Approach: | They propose to use zoning information to incorporate into argument mining tasks . they add zonation labels predicted by an off-the-shelf model to the beginning of each sentence . |
| Outcome: | The proposed models improve argument mining models without additional annotation cost. |
Transforming Visual Scene Graphs to Image Captions (2023.acl-long)
Copied to clipboard
Xu Yang, Jiawei Peng, Zihua Wang, Haiyang Xu, Qinghao Ye, Chenliang Li, Songfang Huang, Fei Huang, Zhangzikang Li, Yu Zhang
| Challenge: | Existing approaches to generate captions using image captioning are based on multi-head attention (MHA) |
| Approach: | They propose to transform scene graphs into more descriptive captions by using multi-head attention to build a Graph Neural Network (GNN) . they construct a Mixture-of-Expert (MOE)-based decoder where each expert is built on MHA for discriminating the graph embeddings to generate different kinds of words. |
| Outcome: | The proposed framework can generate captions from multiple visual features and objects . it is based on a mixture-of-expert (MOE)-based decoder based upon MHA . |
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. |
Interpreting and Exploiting Functional Specialization in Multi-Head Attention under Multi-task Learning (2023.emnlp-main)
Copied to clipboard
| Challenge: | Experimental results show that multi-head attention module evolves functional specialization after multi-task training. |
| Approach: | They propose a method to quantify the degree of functional specialization in multi-head attention . they propose 'multi-task training' method to increase functional specialisation and mitigate negative information transfer . |
| Outcome: | The proposed method increases functional specialization and mitigates negative information transfer in multi-task learning without adding any parameters. |
Mixture-of-Modules: Reinventing Transformers as Dynamic Assemblies of Modules (2024.emnlp-main)
Copied to clipboard
| Challenge: | Empirical results show that MoMs consistently outperform vanilla transformers . |
| Approach: | They propose an architecture that allows for a mixture-of-modules computation that uses a finite set of modules defined by multi-head attention and feed-forward networks. |
| Outcome: | The proposed architecture outperforms vanilla Transformers and their variants in multiple ways. |