How Much Attention Do You Need? A Granular Analysis of Neural Machine Translation Architectures (P18-1)
Copied to clipboard
| Challenge: | Neural Machine Translation (NMT) has been replaced by convolutional or self-attentional approaches. |
| Approach: | They propose an architecture definition language that allows for a flexible combination of common building blocks. |
| Outcome: | The proposed architectures can bring recurrent and convolutional models close to the Transformer architecture, but not using self-attention. |
Similar Papers
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. |
Why Self-Attention? A Targeted Evaluation of Neural Machine Translation Architectures (D18-1)
Copied to clipboard
| Challenge: | Recent studies show that non-recurrent architectures outperform RNNs in neural machine translation. |
| Approach: | They hypothesize that CNNs and self-attentional networks could extract semantic features from source text. |
| Outcome: | The proposed architectures outperform RNNs on two tasks: subject-verb agreement and word sense disambiguation. |
Fixed Encoder Self-Attention Patterns in Transformer-Based Machine Translation (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies have shown that attention heads learn simple positional patterns . |
| Approach: | They propose to replace all but one attention head of each encoder layer with simple fixed – non-learnable – attentive patterns that are solely based on position and do not require external knowledge. |
| Outcome: | The proposed model improves translation quality and improves BLEU scores by up to 3 points in low-resource scenarios. |
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. |
Multi-Granularity Self-Attention for Neural Machine Translation (D19-1)
Copied to clipboard
| Challenge: | Existing neural machine translation models use a deep multi-head self-attention network with no explicit phrase information. |
| Approach: | They propose a neural network that combines multi-head self-attention and phrase modeling to train attention heads to attend to phrases in either n-gram or syntactic formalisms. |
| Outcome: | The proposed approach improves on English-to-German and NIST Chinese-to English translation tasks. |
Do Multilingual Neural Machine Translation Models Contain Language Pair Specific Attention Heads? (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent studies on multilingual representations focus on whether there is an emergence of language-independent representations or whether multilingual models partition their weights among different languages. |
| Approach: | They analyze encoder self-attention and encoder-decoder attention heads in a multilingual neural translation model. |
| Outcome: | The proposed model is based on a multilingual neural translation model with a language-independent representation. |
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. |
Training Deeper Neural Machine Translation Models with Transparent Attention (D18-1)
Copied to clipboard
| Challenge: | Existing NMT models are shallow in comparison to convolutional models used for both text and vision tasks. |
| Approach: | They propose to modify the attention mechanism to ease the optimization of deeper models by a simple modification to the seq2seq with attention paradigm. |
| Outcome: | The proposed model achieves consistent gains of 0.7-1.1 BLEU on the benchmark WMT’14 English-German and WMT'15 Czech-English tasks. |
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 . |
Character-Level Translation with Self-attention (2020.acl-main)
Copied to clipboard
| Challenge: | Existing models for character-level neural machine translation operate on word-level, which makes them memory inefficient because of large vocabulary sizes. |
| Approach: | They propose a transformer-based model and a novel variant that uses convolutions to combine information from nearby characters to facilitate character interactions. |
| Outcome: | The proposed model outperforms the standard transformer model and learns more robust character alignments on bilingual and multilingual translation datasets. |