Challenge: Large-scale transformers have been shown to improve neural machine translation performance but training these wider and deeper networks could be extremely memory intensive.
Approach: They propose a multi-split based reversible transformer and a backpropagation algorithm that does not need to store activations for most layers.
Outcome: The proposed model outperforms the vanilla transformer by at least 1.4 BLEU points in three datasets.

Similar Papers

Learning Deep Transformer Models for Machine Translation (P19-1)

Copied to clipboard

Challenge: Neural machine translation models have advanced the previous state-of-the-art by learning mappings between sequences via neural networks and attention mechanisms.
Approach: They propose to use layer normalization to pass the combination of previous layers to the next layer to improve the model.
Outcome: The proposed model outperforms the shallow Transformer-Big/Base baseline model on English-German and Chinese-English tasks by 0.4-2.4 BLEU points.
Syntactically Supervised Transformers for Faster Neural Machine Translation (P19-1)

Copied to clipboard

Challenge: Standard decoders for neural machine translation generate a single token per timestep, which slows inference . a series of controlled experiments demonstrates that SynST decodes sentences 5x faster than the baseline autoregressive Transformer.
Approach: They propose a syntactically supervised Transformer that generates all target tokens in one shot . synST is a variant of the Transformer architecture that autoregressively predicts a chunked parse tree .
Outcome: The proposed method decodes sentences 5x faster than the baseline method on En-De and En-Fr datasets while achieving higher BLEU scores.
Rethinking Document-level Neural Machine Translation (2022.findings-acl)

Copied to clipboard

Challenge: Neural machine translation models are weak enough for document-level translation . current models only translate sentences individually, resulting in poor document coherence .
Approach: They propose to use the original Transformer model to test document-level neural machine translation . they find that the original transformer models can achieve strong results for document translation if trained properly .
Outcome: The proposed model outperforms sentence-level models on nine datasets and two sentence- level datasets across six languages.
Multi-Unit Transformers for Neural Machine Translation (2020.emnlp-main)

Copied to clipboard

Challenge: Experimental results show that the MUTE models outperform the Transformer-Base by up to +1.52, +1.99 and +1.00 BLEU points, with only a mild drop in inference speed (about 3.1%).
Approach: They propose to use multiple parallel units to promote the expressiveness of the Transformer by introducing diverse and complementary units.
Outcome: The proposed models outperform the Transformer-Base model with only a mild drop in inference speed (about 3.1%).
Discriminative Reranking for Neural Machine Translation (2021.acl-long)

Copied to clipboard

Challenge: reranking models allow the integration of rich features to select a better output hypothesis within an n-best list or lattice.
Approach: They use discriminative reranking to train a large transformer architecture to train an ranked list of hypotheses.
Outcome: Experiments on four WMT directions show that discriminative reranking improves translation quality.
Self-generated Replay Memories for Continual Neural Machine Translation (2024.naacl-long)

Copied to clipboard

Challenge: Neural Machine Translation systems exhibit strong performance in several different languages, but their ability to learn continuously is limited by catastrophic forgetting.
Approach: They propose a method that leverages a key property of encoder-decoder Transformers, i.e. their generative ability, to continuously learn Neural Machine Translation systems.
Outcome: The proposed approach can counteract catastrophic forgetting without explicit memorization of training data.
Multi-layer Representation Fusion for Neural Machine Translation (C18-1)

Copied to clipboard

Challenge: Neural machine translation systems require a number of stacked layers for deep models, but the prediction depends on the sentence representation of the top-most layer with no access to low-level representations.
Approach: They propose a multi-layer representation fusion approach to fusing stacked layers to learn a better representation from the stack.
Outcome: The proposed approach yields 0.92 and 0.56 BLEU points over the strong Transformer baseline on IWSLT German-English and NIST Chinese-English MT tasks respectively.
Towards Modeling the Style of Translators in Neural Machine Translation (2021.naacl-main)

Copied to clipboard

Challenge: a key ingredient of neural machine translation is the use of large datasets with different but consistent translation styles . however, the models do not capture the variety of translators' styles from the data . a recent study shows that style-augmented models can capture the style variations of translator .
Approach: They propose to augment a neural machine translation model with translator information . they use TED talk datasets to model and control translator-related stylistic variations .
Outcome: The proposed models capture the style variations of translators and generate translations with different styles on new data.
Fully Quantized Transformer for Machine Translation (2020.findings-emnlp)

Copied to clipboard

Challenge: State-of-the-art neural machine translation methods use huge amounts of parameters.
Approach: They propose an all-inclusive quantization strategy for the Transformer to reduce computational costs and improve translation quality.
Outcome: The proposed method achieves state-of-the-art results on most tasks compared to previous methods .
Multilingual Unsupervised Neural Machine Translation with Denoising Adapters (2021.emnlp-main)

Copied to clipboard

Challenge: Multilingual unsupervised machine translation is a computationally expensive and hard to tune approach . auxiliary parallel data is used to train translation systems from monolingual data .
Approach: They propose to use auxiliary parallel language pairs to train unsupervised machine translations . they propose to add auxiliary languages to pre-trained mBART-50 models with denoising adapters .
Outcome: The proposed approach is on-par with back-translation and allows adding unseen languages incrementally.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations