paper-with-me

Papers

Adversarial Subword Regularization for Robust Neural Machine Translation

2020-04-29 · Findings of the Association for Computational Linguistics 2020 · Jungsoo Park, Mujeen Sung, Jinhyuk Lee, Jaewoo Kang

Exposing diverse subword segmentations to neural machine translation (NMT) models often improves the robustness of machine translation as NMT models can experience various subword candidates. However, the diversification of subword segmentations mostly relies on the pre-trained subword language models from which erroneous segmentations of unseen words are less likely to be sampled. In this paper, we present adversarial subword regularization (ADVSR) to study whether gradient signals during training can be a substitute criterion for exposing diverse subword segmentations. We experimentally show that our model-based adversarial samples effectively encourage NMT models to be less sensitive to segmentation errors and improve the performance of NMT models in low-resource and out-domain datasets.

📄 PDF Abstract BibTeX arXiv:2004.14109

Code (1)

dmis-lab/AdvSR 공식 구현 pytorch

Tasks

Machine TranslationNMTTranslation

Similar Papers 제목 키워드 기반

Single Model Ensemble for Subword Regularized Models in Low-Resource Machine Translation

2022-03-25 · Findings (ACL) 2022 5 · Sho Takase, Tatsuya Hiraoka, Naoaki Okazaki

Subword regularizations use multiple subword segmentations during training to improve the robustness of neural machine translation models. In previous subword regularizations, we use multiple segmentations in the trainin…

Machine TranslationSegmentationTranslation

Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates

2018-04-29 · ACL 2018 7 · Taku Kudo

Subword units are an effective way to alleviate the open vocabulary problems in neural machine translation (NMT). While sentences are usually converted into unique subword sequences, subword segmentation is potentially a…

Language ModelingLanguage ModellingMachine TranslationNMT+2

MaxMatch-Dropout: Subword Regularization for WordPiece

2022-09-09 · COLING 2022 10 · Tatsuya Hiraoka

We present a subword regularization method for WordPiece, which uses a maximum matching algorithm for tokenization. The proposed method, MaxMatch-Dropout, randomly drops words in a search using the maximum matching algor…

Machine TranslationText ClassificationTranslation

Evaluating Robustness to Input Perturbations for Neural Machine Translation

2020-05-01 · ACL 2020 6 · Xing Niu, Prashant Mathur, Georgiana Dinu, Yaser Al-Onaizan

Neural Machine Translation (NMT) models are sensitive to small perturbations in the input. Robustness to such perturbations is typically measured using translation quality metrics such as BLEU on the noisy input. This pa…

Machine TranslationNMTTranslation

BPE-Dropout: Simple and Effective Subword Regularization

2019-10-29 · ACL 2020 6 · Ivan Provilkov, Dmitrii Emelianenko, Elena Voita

Subword segmentation is widely used to address the open vocabulary problem in machine translation. The dominant approach to subword segmentation is Byte Pair Encoding (BPE), which keeps the most frequent words intact whi…

Machine TranslationSegmentationTranslation