Multitask Models for Controlling the Complexity of Neural Machine Translation
We introduce a machine translation task where the output is aimed at audiences of different levels of target language proficiency. We collect a novel dataset of news articles available in English and Spanish and written for diverse reading grade levels. We leverage this dataset to train multitask sequence to sequence models that translate Spanish into English targeted at an easier reading grade level than the original Spanish. We show that multitask models outperform pipeline approaches that translate and simplify text independently.
Code (0)
등록된 구현이 없습니다.
Tasks
ArticlesMachine TranslationTranslationSimilar Papers 제목 키워드 기반
Multitask Finetuning for Improving Neural Machine Translation in Indian Languages
Transformer based language models have led to impressive results across all domains in Natural Language Processing. Pretraining these models on language modeling tasks and finetuning them on downstream tasks such as Text…
Causal Language ModelingLanguage ModelingLanguage ModellingMachine Translation+4Duplex Sequence-to-Sequence Learning for Reversible Machine Translation
Sequence-to-sequence learning naturally has two directions. How to effectively utilize supervision signals from both directions? Existing approaches either require two separate models, or a multitask-learned model but wi…
Machine TranslationTranslationOnline Multitask Learning for Machine Translation Quality Estimation
Large-scale Multitask Learning for Machine Translation Quality Estimation
Statistical Machine Translation Features with Multitask Tensor Networks
We present a three-pronged approach to improving Statistical Machine Translation (SMT), building on recent success in the application of neural networks to SMT. First, we propose new features based on neural networks to …
Machine TranslationTensor NetworksTranslation