Challenge: Existing non-autoregressive neural machine translation models suffer from multimodality problem . multi-modality is not solved by a teacher forcing algorithm, limiting model capability .
Approach: They propose a method that generates multiple reference translations for each source sentence . they compare the NAT output with all references and select the one that best fits the simulated model .
Outcome: The proposed method achieves 29.82 BLEU with only one decoding pass on WMT14 En-De .

Similar Papers

Fully Non-autoregressive Neural Machine Translation: Tricks of the Trade (2021.findings-acl)

Copied to clipboard

Challenge: Existing non-autoregressive neural machine translation models are slow to learn the dependency between output tokens.
Approach: They propose to use fully non-autoregressive neural machine translation (NAT) to predict tokens with single forward of neural networks.
Outcome: The proposed model achieves state-of-the-art results on three translation benchmarks with comparable performance to autoregressive and iterative NAT systems.
How Does Distilled Data Complexity Impact the Quality and Confidence of Non-Autoregressive Machine Translation? (2021.findings-acl)

Copied to clipboard

Challenge: Prior work suggests that distilled training data is less complex than manual translations.
Approach: They propose to use sequence-level knowledge distillation to match autoregressive models' translation quality.
Outcome: The proposed model can match translation quality of autoregressive models with distilled training data.
Multi-Granularity Optimization for Non-Autoregressive Translation (2022.emnlp-main)

Copied to clipboard

Challenge: Non-autoregressive machine translation suffers severe performance deterioration due to the naive independence assumption.
Approach: They propose a method which collects model behaviours on translation segments of various granularities and integrates feedback for backpropagation to reduce latency.
Outcome: Experiments on four benchmark datasets show that the proposed method outperforms baseline models trained with cross-entropy loss and achieves the best performance on WMT’16 EnRo and highly competitive results on WTM’14 EnDe.
Towards Multiple References Era – Addressing Data Leakage and Limited Reference Diversity in Machine Translation Evaluation (2024.findings-acl)

Copied to clipboard

Challenge: Recent research shows a weak correlation between n-gram-based metrics and human evaluations in machine translation tasks.
Approach: They propose to use multiple references generated by LLMs to improve alignment between automatic metrics and human evaluations.
Outcome: The proposed approach improves the alignment between automatic metrics and human evaluations on the WMT22 benchmark with 4 languages and achieves a maximum accuracy gain of 9.5%.
Multi-Task Learning with Shared Encoder for Non-Autoregressive Machine Translation (2021.naacl-main)

Copied to clipboard

Challenge: Existing non-autoregressive machine translation models have shown significant inference speedup but suffer from inferior translation accuracy.
Approach: They propose to use AT as an auxiliary task to transfer AT knowledge to NAT models by knowledge distillation.
Outcome: The proposed method achieves significant improvements over baseline non-Autoregressive machine translation models on WMT14 En-De and WMT16 En-Ro datasets.
Self-Improvement of Non-autoregressive Model via Sequence-Level Distillation (2023.emnlp-main)

Copied to clipboard

Challenge: Existing non-autoregressive Transformers (NAT) models generate the entire sequence in parallel, but the multimodality problem limits their performance.
Approach: They propose a method to generate distilled data by the NAT model itself, eliminating the need for additional teacher networks.
Outcome: The proposed method can generate distilled data by the NAT model without teacher networks and adapt to different NAT models without precise adjustments.
Integrating Translation Memories into Non-Autoregressive Machine Translation (2023.eacl-main)

Copied to clipboard

Challenge: Non-autoregressive machine translation (NAT) has made great progress, but most studies focus on standard translation tasks.
Approach: They propose to train an edit-based NAT model with a Translation Memory (TM) they propose to modify the data presentation and introduce an extra deletion operation to reduce decoding load.
Outcome: The proposed model performs on par with an autoregressive approach while reducing the decoding load.
Progressive Multi-Granularity Training for Non-Autoregressive Translation (2021.findings-acl)

Copied to clipboard

Challenge: Non-autoregressive translation models are weak at learning high-mode knowledge, argues a new study . despite the improved learning difficulty, there are still complicated word orders and structures in the synthetic sentences, making the NAT performance sub-optimal.
Approach: They propose to train non-autoregressive translation models to learn fine-grained lower-mode knowledge . they break down sentence-level examples into three types and increase granularities .
Outcome: The proposed method improves phrase translation accuracy and model reordering ability against strong NAT baselines.
Knowledge Distillation for Multilingual Unsupervised Neural Machine Translation (2020.acl-main)

Copied to clipboard

Challenge: Unsupervised neural machine translation (UNMT) can only translate between a single language pair and cannot produce translation results for multiple language pairs at the same time.
Approach: They propose a method to translate between 13 languages using a single encoder and a decoder . they propose two knowledge distillation methods to further enhance multilingual UNMT performance .
Outcome: The proposed method improves translation performance for all languages using multilingual data.
Improving Non-autoregressive Neural Machine Translation with Monolingual Data (2020.acl-main)

Copied to clipboard

Challenge: Neural machine translation is usually done via knowledge distillation from an autoregressive (AR) model.
Approach: They leverage large monolingual corpora to improve the NAR model's performance by transferring the autoregressive model' s generalization ability while preventing overfitting.
Outcome: The proposed methods on the WMT14 En-De and WMT16 En-Ro news translation tasks show that monolingual data augmentation improves the NAR model to approach the teacher AR model’s performance.

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