paper-with-me

Papers

Self-Induced Curriculum Learning in Neural Machine Translation

2019-09-25 · Dana Ruiter, Cristina España-Bonet, Josef van Genabith

Self-supervised neural machine translation (SS-NMT) learns how to extract/select suitable training data from comparable (rather than parallel) corpora and how to translate, in a way that the two tasks support each other in a virtuous circle. SS-NMT has been shown to be competitive with state-of-the-art unsupervised NMT. In this study we provide an in-depth analysis of the sampling choices the SS-NMT model takes during training. We show that, without it having been told to do so, the model selects samples of increasing (i) complexity and (ii) task-relevance in combination with (iii) a denoising curriculum. We observe that the dynamics of the mutual-supervision of both system internal representation types is vital for the extraction and hence translation performance. We show that in terms of the human Gunning-Fog Readability index (GF), SS-NMT starts by extracting and learning from Wikipedia data suitable for high school (GF=10--11) and quickly moves towards content suitable for first year undergraduate students (GF=13).

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingMachine TranslationNMTTranslation

Similar Papers 제목 키워드 기반

Self-Induced Curriculum Learning in Self-Supervised Neural Machine Translation

2020-04-07 · EMNLP 2020 11 · Dana Ruiter, Josef van Genabith, Cristina España-Bonet

Self-supervised neural machine translation (SSNMT) jointly learns to identify and select suitable training data from comparable (rather than parallel) corpora and to translate, in a way that the two tasks support each ot…

DenoisingMachine TranslationTranslation

Competence-based Curriculum Learning for Multilingual Machine Translation

2021-09-09 · Findings (EMNLP) 2021 11 · Mingliang Zhang, Fandong Meng, Yunhai Tong, Jie zhou

Currently, multilingual machine translation is receiving more and more attention since it brings better performance for low resource languages (LRLs) and saves more space. However, existing multilingual machine translati…

Machine TranslationTranslation

Self-Guided Curriculum Learning for Neural Machine Translation

2021-05-10 · ACL (IWSLT) 2021 8 · Lei Zhou, Liang Ding, Kevin Duh, Shinji Watanabe 외

In the field of machine learning, the well-trained model is assumed to be able to recover the training labels, i.e. the synthetic labels predicted by the model should be as close to the ground-truth labels as possible. I…

Machine TranslationNMTSentenceTranslation

An Empirical Exploration of Curriculum Learning for Neural Machine Translation

2018-11-02 · Xuan Zhang, Gaurav Kumar, Huda Khayrallah, Kenton Murray 외

Machine translation systems based on deep neural networks are expensive to train. Curriculum learning aims to address this issue by choosing the order in which samples are presented during training to help train better m…

Machine TranslationTranslation

Self-Paced Learning for Neural Machine Translation

2020-10-09 · EMNLP 2020 11 · Yu Wan, Baosong Yang, Derek F. Wong, Yikai Zhou 외

Recent studies have proven that the training of neural machine translation (NMT) can be facilitated by mimicking the learning process of humans. Nevertheless, achievements of such kind of curriculum learning rely on the …

Machine TranslationNMTSentenceTranslation