Attention Calibration for Transformer in Neural Machine Translation (2021.acl-long)
Copied to clipboard
| Challenge: | Attention mechanisms have been ubiquitous in neural machine translation (NMT) however, many studies doubt whether highlyattended inputs have a large impact on the model outputs. |
| Approach: | They propose to introduce a mask perturbation model that automatically evaluates each input’s contribution to the model outputs. |
| Outcome: | The proposed model is more uniform at lower layers while more concentrated on the specific inputs at higher layers. |
Similar Papers
Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictions (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Using attention weights, we show that NMT models make alignment errors by relying on uninformative tokens from the source sequence. |
| Approach: | They propose to use attention weights to regulate alignment errors in NMT models . they propose methods that largely reduce the word alignment error rate compared to standard induced alignments from attention weighted tokens. |
| Outcome: | The proposed methods reduce the word alignment error rate compared to standard induced alignments from attention weights. |
Alleviating the Inequality of Attention Heads for Neural Machine Translation (2022.coling-1)
Copied to clipboard
| Challenge: | Recent studies show that the attention heads in Transformer are not equal. |
| Approach: | They propose a masking method to mask attention heads in Transformer . they empirically validate the inequality and propose 'head mask' method to avoid bottleneck . |
| Outcome: | The proposed masking method improves translation performance on multiple languages . it can be used to remove a small subset of heads without affecting performance . |
Speeding up Transformer Decoding via an Attention Refinement Network (2022.coling-1)
Copied to clipboard
| Challenge: | Extensive experiments on ten WMT machine translation tasks show that the proposed model yields an average of 1.35x faster (with almost no decrease in BLEU) |
| Approach: | They propose a weighted residual network which reconstructs attention by reusing the features across layers. |
| Outcome: | The proposed model is 1.35x faster than the state-of-the-art inference model on translation tasks compared to AAN and SAN models with fewer parameter numbers . |
Synchronous Syntactic Attention for Transformer Neural Machine Translation (2021.acl-srw)
Copied to clipboard
| Challenge: | Existing syntaxbased NMT models use monolingual syntactic information on either side or both. |
| Approach: | They propose a mechanism that synchronizes source-side and target-side syntactic self-attentions by minimizing the difference between target- and target side self- attentions mapped by the encoder-decoder attention matrix. |
| Outcome: | The proposed method improves translation performance on WMT14 En-De, WMT16 En-Ro, and ASPEC Ja-En (up to +0.38 points in BLEU). |
Enhancing Machine Translation with Dependency-Aware Self-Attention (2020.acl-main)
Copied to clipboard
| Challenge: | Currently, most neural machine translation models rely on pairs of parallel sentences, assuming syntactic information is automatically learned by an attention mechanism. |
| Approach: | They propose a parameter-free, dependency-aware self-attention mechanism that integrates syntactic knowledge into a Transformer model and propose 'a parameter free approach' they also propose - a novel mechanism that improves translation quality for long sentences and in low-resource scenarios. |
| Outcome: | The proposed approach improves translation quality on English-German and English-Turkish translation tasks and in low-resource scenarios. |
Recurrent Attention for Neural Machine Translation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent research questions the importance of dot-product self-attention in Transformer models and shows that most attention heads learn simple positional patterns. |
| Approach: | They propose a novel mechanism to replace dot-product self-attention with a recurrent atteNtion mechanism that directly learns attention weights without token-to-token interaction. |
| Outcome: | The proposed model outperforms the Transformer model on translation tasks with fewer parameters and inference time. |
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. |
Learning to Deceive with Attention-Based Explanations (2020.acl-main)
Copied to clipboard
| Challenge: | Attention mechanisms are ubiquitous components in neural network architectures and are often claimed to confer interpretability. |
| Approach: | They propose a method for training models to produce deceptive attention masks by combining weights assigned to designated impermissible tokens with a weighted sum. |
| Outcome: | The proposed method reduces the weight assigned to designated impermissible tokens while still using them across multiple models and tasks. |
Losing Heads in the Lottery: Pruning Transformer Attention in Neural Machine Translation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Recent research shows that attention heads are not confident in their decisions and can be pruned. |
| Approach: | They apply the lottery ticket hypothesis to prune heads in early training . they find that the pruned model is 1.5 times faster at inference . |
| Outcome: | The proposed method is 1.5 times faster at inference, but at the cost of longer training. |
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. |