paper-with-me

Papers

Subword-Delimited Downsampling for Better Character-Level Translation

2022-12-02 · Lukas Edman, Antonio Toral, Gertjan van Noord

Subword-level models have been the dominant paradigm in NLP. However, character-level models have the benefit of seeing each character individually, providing the model with more detailed information that ultimately could lead to better models. Recent works have shown character-level models to be competitive with subword models, but costly in terms of time and computation. Character-level models with a downsampling component alleviate this, but at the cost of quality, particularly for machine translation. This work analyzes the problems of previous downsampling methods and introduces a novel downsampling method which is informed by subwords. This new downsampling method not only outperforms existing downsampling methods, showing that downsampling characters can be done without sacrificing quality, but also leads to promising performance compared to subword models for translation.

📄 PDF Abstract BibTeX arXiv:2212.01304

Code (1)

leukas/sdd 공식 구현 pytorch

Tasks

Machine TranslationTranslation

Similar Papers 제목 키워드 기반

Patching Leaks in the Charformer for Efficient Character-Level Generation

2022-05-27 · Lukas Edman, Antonio Toral, Gertjan van Noord

Character-based representations have important advantages over subword-based ones for morphologically rich languages. They come with increased robustness to noisy input and do not need a separate tokenization step. Howev…

DecoderNMTTranslation

Patching Leaks in the Charformer for Generative Tasks

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Character-based representations have important advantages over subword-based ones, including increased robustness to noisy input and removing the need of tokenization preprocessing. However, they also have a crucial disa…

DecoderNMT

Why don't people use character-level machine translation?

2021-10-15 · Jindřich Libovický, Helmut Schmid, Alexander Fraser

We present a literature and empirical survey that critically assesses the state of the art in character-level modeling for machine translation (MT). Despite evidence in the literature that character-level systems are com…

Machine TranslationTranslation

Why don’t people use character-level machine translation?

2022-05-01 · Findings (ACL) 2022 5 · Jindřich Libovický, Helmut Schmid, Alexander Fraser

We present a literature and empirical survey that critically assesses the state of the art in character-level modeling for machine translation (MT). Despite evidence in the literature that character-level systems are com…

Machine TranslationTranslation

When is Char Better Than Subword: A Systematic Study of Segmentation Algorithms for Neural Machine Translation

2021-08-01 · ACL 2021 5 · Jiahuan Li, Yutong Shen, ShuJian Huang, Xinyu Dai 외

Subword segmentation algorithms have been a \textit{de facto} choice when building neural machine translation systems. However, most of them need to learn a segmentation model based on some heuristics, which may produce …

Machine TranslationNMTSegmentationTranslation