paper-with-me

홈 › Papers

Improving Fluency of Non-Autoregressive Machine Translation

2020-04-07 · Zdeněk Kasner, Jindřich Libovický, Jindřich Helcl

Non-autoregressive (nAR) models for machine translation (MT) manifest superior decoding speed when compared to autoregressive (AR) models, at the expense of impaired fluency of their outputs. We improve the fluency of a nAR model with connectionist temporal classification (CTC) by employing additional features in the scoring model used during beam search decoding. Since the beam search decoding in our model only requires to run the network in a single forward pass, the decoding speed is still notably higher than in standard AR models. We train models for three language pairs: German, Czech, and Romanian from and into English. The results show that our proposed models can be more efficient in terms of decoding speed and still achieve a competitive BLEU score relative to AR models.

📄 PDF Abstract BibTeX arXiv:2004.03227

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationTranslation

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Fluency and Faithfulness in Human and Machine Literary Translation

2026-05-14 · Sarah Griebel, Ted Underwood arxiv

Literary translation requires balancing target-language fluency with faithfulness to the source. Recent large language models (LLMs) often produce fluent translations, but it remains unclear whether fluency corresponds t…

Lack of Fluency is Hurting Your Translation Model

2022-05-24 · Jaehyo Yoo, Jaewoo Kang

Many machine translation models are trained on bilingual corpus, which consist of aligned sentence pairs from two different languages with same semantic. However, there is a qualitative discrepancy between train and test…

Machine TranslationmodelSentenceTranslation

Feeding Two Birds or Favoring One? Adequacy-Fluency Tradeoffs in Evaluation and Meta-Evaluation of Machine Translation

2025-09-24 · Behzad Shayegh, Jan-Thorsten Peter, David Vilar, Tobias Domhan 외 arxiv

We investigate the tradeoff between adequacy and fluency in machine translation. We show the severity of this tradeoff at the evaluation level and analyze where popular metrics fall within it. Essentially, current metric…

Machine Translation

Improve the Evaluation of Fluency Using Entropy for Machine Translation Evaluation Metrics

2015-08-10 · Hui Yu, Xiaofeng Wu, Wenbin Jiang, Qun Liu 외

The widely-used automatic evaluation metrics cannot adequately reflect the fluency of the translations. The n-gram-based metrics, like BLEU, limit the maximum length of matched fragments to n and cannot catch the matched…

Machine TranslationSentenceTranslation

Generating Fluent Translations from Disfluent Text Without Access to Fluent References: IIT Bombay@IWSLT2020

2020-07-01 · WS 2020 7 · Nikhil Saini, Jyotsana Khatri, Preethi Jyothi, Pushpak Bhattacharyya

Machine translation systems perform reasonably well when the input is well-formed speech or text. Conversational speech is spontaneous and inherently consists of many disfluencies. Producing fluent translations of disflu…

DenoisingMachine TranslationTranslation