| Challenge: | a large proportion of model parameters can be frozen during adaptation with minimal or no reduction in translation quality. |
| Approach: | They propose gradient-based domain adaptation methods for self-attentive machine translation models . they encourage structured sparsity in the set of offset tensors during learning . |
| Outcome: | The proposed method achieves high space and time efficiency using sparse models . the results compare the proposed method with incremental adaptation . |
Similar Papers
Extreme Adaptation for Personalized Neural Machine Translation (P18-2)
Copied to clipboard
| Challenge: | Existing models that capture speaker-related variations do not include explicit information about the speaker. |
| Approach: | They propose a method that adapts the bias of the output softmax to each particular user . they propose to model speaker-related variations as an additional bias vector in the softmax layer . |
| Outcome: | The proposed technique improves translation accuracy and better reflection of speaker traits in target text. |
Domain Differential Adaptation for Neural Machine Translation (D19-56)
Copied to clipboard
| Challenge: | Neural networks are data hungry and domain sensitive, so it is difficult to obtain labeled data for every domain. |
| Approach: | They propose a framework for domain adaptation where we model the difference between domains instead of smoothing over them. |
| Outcome: | The proposed framework improves on domain adaptation in multiple experimental settings. |
Simple, Scalable Adaptation for Neural Machine Translation (D19-1)
Copied to clipboard
| Challenge: | Recent advances in deep learning have led to significantly improved quality on Neural Machine Translation (NMT) however, performance on out-of-domain data or low resource languages remains poor. |
| Approach: | They propose a simple yet efficient approach for adapting pre-trained models to multiple tasks simultaneously. |
| Outcome: | The proposed approach is on par with full fine-tuning on domain adaptation and massively multilingual NMT on a massively multilingual dataset. |
Improving the Quality Trade-Off for Neural Machine Translation Multi-Domain Adaptation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Building neural machine translation systems to perform well on a specific target domain remains a challenge. |
| Approach: | They propose to train a single NMT system per language pair that performs well across multiple domains. |
| Outcome: | The proposed approach improves the Pareto frontier on this task. |
Pruning-then-Expanding Model for Domain Adaptation of Neural Machine Translation (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for domain adaptation suffer from catastrophic forgetting, large domain divergence, and model explosion. |
| Approach: | They propose a method which prunes the model and keeps the important neurons or parameters responsible for both general-domain and in-domain translation. |
| Outcome: | The proposed method improves on different language pairs and domains compared with strong baselines. |
Distilling Multiple Domains for Neural Machine Translation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Neural machine translation is a powerful tool for high-resource domains, but performance suffers when the input domain is low-resourced. |
| Approach: | They propose a framework for training a single multi-domain neural machine translation model that can translate multiple domains without increasing inference time or memory usage. |
| Outcome: | The proposed model improves translation on both high- and low-resource domains over strong multi-domain baselines and is robust under noisy data conditions. |
Evaluating Domain Adaptation for Machine Translation Across Scenarios (L18-1)
Copied to clipboard
| Challenge: | Statistical machine translation (SMT) has been the dominant approach for the last 20 years, with neural machine translation becoming the new main paradigm in academic research and the industry. |
| Approach: | They propose to compare domain-adapted statistical and neural machine translation systems on three different domains and language pairs with varying degrees of domain specificity and available training data. |
| Outcome: | The proposed system is the best choice for translation, with marked impacts for domains with higher specificity. |
Domain Adaptive Inference for Neural Machine Translation (P19-1)
Copied to clipboard
| Challenge: | Neural Machine Translation models are effective when trained on broad domains with large datasets, such as news translation. |
| Approach: | They propose a novel approach for adaptive ensemble weighting for Neural Machine Translation by extending Bayesian Interpolation with source information. |
| Outcome: | The proposed approach improves performance on Spanish-English and English-German tasks without the need for the domain label. |
A Stochastic Decoder for Neural Machine Translation (P18-1)
Copied to clipboard
| Challenge: | Neural machine translation models do not account for local lexical and syntactic variation in parallel corpora. |
| Approach: | They propose a deep generative model of machine translation which incorporates a chain of latent variables to account for local lexical and syntactic variation in parallel corpora. |
| Outcome: | The proposed model consistently improves over strong baselines on several different language pairs. |
The Trade-offs of Domain Adaptation for Neural Language Models (2022.acl-long)
Copied to clipboard
| Challenge: | Neural Language Models (LMs) trained on large generic training sets have been shown to be effective at adapting to smaller, specific target domains for language modeling and other downstream tasks. |
| Approach: | They propose a framework for a Neural Language Models (LM) to be presented in a common framework. |
| Outcome: | The proposed framework highlights similarities and subtle differences between adaptation techniques and the framework. |