Search Results for author:
Found 7 papers, 2 papers with code
Language Tokens: Simply Improving Zero-Shot Multi-Aligned Translation in Encoder-Decoder Models
In a WMT-based setting, we see 1. 3 and 0. 4 BLEU points improvement for the zero-shot setting, and when using direct data for training, respectively, while from-English performance improves by 4. 17 and 0. 85 BLEU points.
How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation
In this paper, we present a comprehensive evaluation of GPT models for machine translation, covering various aspects such as quality of different GPT models in comparison with state-of-the-art research and commercial systems, effect of prompting strategies, robustness towards domain shifts and document-level translation.
Domain Specific Sub-network for Multi-Domain Neural Machine Translation
This paper presents Domain-Specific Sub-network (DoSS).
Language Tokens: A Frustratingly Simple Approach Improves Zero-Shot Performance of Multilingual Translation
In a WMT evaluation campaign, From-English performance improves by 4. 17 and 2. 87 BLEU points, in the zero-shot setting, and when direct data is available for training, respectively.
Ensembling of Distilled Models from Multi-task Teachers for Constrained Resource Language Pairs
This paper describes our submission to the constrained track of WMT21 shared news translation task.
Scalable and Efficient MoE Training for Multitask Multilingual Models
By combining the efficient system and training methods, we are able to significantly scale up large multitask multilingual models for language generation which results in a great improvement in model accuracy.
Score Combination for Improved Parallel Corpus Filtering for Low Resource Conditions
For the mBART finetuning setup, provided by the organizers, our method shows 7% and 5% relative improvement over baseline, in sacreBLEU score on the test set for Pashto and Khmer respectively.
