paper-with-me

홈 › Papers

Focus on the Target's Vocabulary: Masked Label Smoothing for Machine Translation

2022-03-06 · Liang Chen, Runxin Xu, Baobao Chang

Label smoothing and vocabulary sharing are two widely used techniques in neural machine translation models. However, we argue that simply applying both techniques can be conflicting and even leads to sub-optimal performance. When allocating smoothed probability, original label smoothing treats the source-side words that would never appear in the target language equally to the real target-side words, which could bias the translation model. To address this issue, we propose Masked Label Smoothing (MLS), a new mechanism that masks the soft label probability of source-side words to zero. Simple yet effective, MLS manages to better integrate label smoothing with vocabulary sharing. Our extensive experiments show that MLS consistently yields improvement over original label smoothing on different datasets, including bilingual and multilingual translation from both translation quality and model's calibration. Our code is released at https://github.com/PKUnlp-icler/MLS

📄 PDF Abstract BibTeX arXiv:2203.02889

Code (2)

chenllliang/MLS 공식 구현 pytorch
pkunlp-icler/mls 공식 구현 pytorch

Tasks

Machine TranslationTranslation

Methods 이 논문이 사용한 방법론

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Focus on the Target’s Vocabulary: Masked Label Smoothing for Machine Translation

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Label smoothing and vocabulary sharing are two widely used techniques in neural machine translation models. However, we argue that jointly adopting these two techniques can be conflicting and even leads to sub-optimal pe…

Machine TranslationTranslation

Focus on the Target's Vocabulary: Masked Label Smoothing for Machine Translation

2021-09-17 · ACL ARR September 2021 9 · Anonymous

Label smoothing and vocabulary sharing are two widely used techniques in neural machine translation models. However, we argue that jointly adopting these two techniques can be conflicting and even leads to sub-optimal pe…

Machine TranslationTranslation

Focus on the Target’s Vocabulary: Masked Label Smoothing for Machine Translation

2022-05-01 · ACL 2022 5 · Liang Chen, Runxin Xu, Baobao Chang

Label smoothing and vocabulary sharing are two widely used techniques in neural machine translation models. However, we argue that simply applying both techniques can be conflicting and even leads to sub-optimal performa…

Machine TranslationTranslation

Text Smoothing: Enhance Various Data Augmentation Methods on Text Classification Tasks

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Before entering the neural network, a token needs to be converted to its one-hot representation, which is a discrete distribution of the vocabulary. Smoothed representation is the probability of candidate tokens obtained…

Data AugmentationLanguage ModelingLanguage ModellingSentence+2

Text Smoothing: Enhance Various Data Augmentation Methods on Text Classification Tasks

2022-02-28 · ACL 2022 5 · Xing Wu, Chaochen Gao, Meng Lin, Liangjun Zang 외

Before entering the neural network, a token is generally converted to the corresponding one-hot representation, which is a discrete distribution of the vocabulary. Smoothed representation is the probability of candidate …

Data AugmentationLanguage ModelingLanguage ModellingSentence+2