paper-with-me

Papers

Boosting Unsupervised Machine Translation with Pseudo-Parallel Data

2023-10-22 · Ivana Kvapilíková, Ondřej Bojar

Even with the latest developments in deep learning and large-scale language modeling, the task of machine translation (MT) of low-resource languages remains a challenge. Neural MT systems can be trained in an unsupervised way without any translation resources but the quality lags behind, especially in truly low-resource conditions. We propose a training strategy that relies on pseudo-parallel sentence pairs mined from monolingual corpora in addition to synthetic sentence pairs back-translated from monolingual corpora. We experiment with different training schedules and reach an improvement of up to 14.5 BLEU points (English to Ukrainian) over a baseline trained on back-translated data only.

📄 PDF Abstract BibTeX arXiv:2310.14262

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingMachine TranslationSentenceTranslationUnsupervised Machine Translation

Similar Papers 제목 키워드 기반

Unsupervised Bitext Mining and Translation via Self-trained Contextual Embeddings

2020-10-15 · Phillip Keung, Julian Salazar, Yichao Lu, Noah A. Smith

We describe an unsupervised method to create pseudo-parallel corpora for machine translation (MT) from unaligned text. We use multilingual BERT to create source and target sentence embeddings for nearest-neighbor search …

Machine TranslationSentenceSentence EmbeddingsTranslation

Filtering Back-Translated Data in Unsupervised Neural Machine Translation

2020-12-01 · COLING 2020 8 · Jyotsana Khatri, Pushpak Bhattacharyya

Unsupervised neural machine translation (NMT) utilizes only monolingual data for training. The quality of back-translated data plays an important role in the performance of NMT systems. In back-translation, all generated…

Domain AdaptationMachine TranslationNMTSentence+1

USCORE: An Effective Approach to Fully Unsupervised Evaluation Metrics for Machine Translation

2022-02-21 · Jonas Belouadi, Steffen Eger

The vast majority of evaluation metrics for machine translation are supervised, i.e., (i) are trained on human scores, (ii) assume the existence of reference translations, or (iii) leverage parallel data. This hinders th…

Machine TranslationParallel Corpus MiningSentenceSentence Embeddings+1

Contrastive Clustering to Mine Pseudo Parallel Data for Unsupervised Translation

2021-09-29 · ICLR 2022 4 · Xuan-Phi Nguyen, Hongyu Gong, Yun Tang, Changhan Wang 외

Modern unsupervised machine translation systems mostly train their models by generating synthetic parallel training data from large unlabeled monolingual corpora of different languages through various means, such as iter…

ClusteringMachine TranslationTranslationUnsupervised Machine Translation

Data Augmentation with Unsupervised Machine Translation Improves the Structural Similarity of Cross-lingual Word Embeddings

2020-05-30 · ACL 2021 5 · Sosuke Nishikawa, Ryokan Ri, Yoshimasa Tsuruoka

Unsupervised cross-lingual word embedding (CLWE) methods learn a linear transformation matrix that maps two monolingual embedding spaces that are separately trained with monolingual corpora. This method relies on the ass…

Cross-Lingual Word EmbeddingsData AugmentationMachine TranslationTranslation+2