paper-with-me

Papers

Towards Reinforcement Learning for Pivot-based Neural Machine Translation with Non-autoregressive Transformer

2021-09-27 · Evgeniia Tokarchuk, Jan Rosendahl, Weiyue Wang, Pavel Petrushkov, Tomer Lancewicki, Shahram Khadivi, Hermann Ney

Pivot-based neural machine translation (NMT) is commonly used in low-resource setups, especially for translation between non-English language pairs. It benefits from using high resource source-pivot and pivot-target language pairs and an individual system is trained for both sub-tasks. However, these models have no connection during training, and the source-pivot model is not optimized to produce the best translation for the source-target task. In this work, we propose to train a pivot-based NMT system with the reinforcement learning (RL) approach, which has been investigated for various text generation tasks, including machine translation (MT). We utilize a non-autoregressive transformer and present an end-to-end pivot-based integrated model, enabling training on source-target data.

📄 PDF Abstract BibTeX arXiv:2109.13097

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationNMTreinforcement-learningReinforcement Learning (RL)Text GenerationTranslation

Similar Papers 제목 키워드 기반

Multilingual Non-Autoregressive Machine Translation without Knowledge Distillation

2025-02-06 · Chenyang Huang, Fei Huang, Zaixiang Zheng, Osmar R. Zaïane 외

Multilingual neural machine translation (MNMT) aims at using one single model for multiple translation directions. Recent work applies non-autoregressive Transformers to improve the efficiency of MNMT, but requires expen…

Knowledge DistillationMachine TranslationTranslation

Integrated Training for Sequence-to-Sequence Models Using Non-Autoregressive Transformer

2021-09-27 · ACL (IWSLT) 2021 8 · Evgeniia Tokarchuk, Jan Rosendahl, Weiyue Wang, Pavel Petrushkov 외

Complex natural language applications such as speech translation or pivot translation traditionally rely on cascaded models. However, cascaded models are known to be prone to error propagation and model discrepancy probl…

Machine TranslationTranslation

Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation

2019-06-22 · ACL 2019 7 · Chenze Shao, Yang Feng, Jinchao Zhang, Fandong Meng 외

Non-Autoregressive Transformer (NAT) aims to accelerate the Transformer model through discarding the autoregressive mechanism and generating target words independently, which fails to exploit the target sequential inform…

DecoderMachine TranslationSentenceTranslation

Non-Autoregressive Machine Translation with Latent Alignments

2020-04-16 · EMNLP 2020 11 · Chitwan Saharia, William Chan, Saurabh Saxena, Mohammad Norouzi

This paper presents two strong methods, CTC and Imputer, for non-autoregressive machine translation that model latent alignments with dynamic programming. We revisit CTC for machine translation and demonstrate that a sim…

Machine TranslationTranslation

Rephrasing the Reference for Non-Autoregressive Machine Translation

2022-11-30 · Chenze Shao, Jinchao Zhang, Jie zhou, Yang Feng

Non-autoregressive neural machine translation (NAT) models suffer from the multi-modality problem that there may exist multiple possible translations of a source sentence, so the reference sentence may be inappropriate f…

Machine TranslationSentenceTranslation