paper-with-me

홈 › Papers

Choose the Final Translation from NMT and LLM hypotheses Using MBR Decoding: HW-TSC's Submission to the WMT24 General MT Shared Task

2024-09-23 · Zhanglin Wu, Daimeng Wei, Zongyao Li, Hengchao Shang, Jiaxin Guo, Shaojun Li, Zhiqiang Rao, Yuanchang Luo, Ning Xie, Hao Yang

This paper presents the submission of Huawei Translate Services Center (HW-TSC) to the WMT24 general machine translation (MT) shared task, where we participate in the English to Chinese (en2zh) language pair. Similar to previous years' work, we use training strategies such as regularized dropout, bidirectional training, data diversification, forward translation, back translation, alternated training, curriculum learning, and transductive ensemble learning to train the neural machine translation (NMT) model based on the deep Transformer-big architecture. The difference is that we also use continue pre-training, supervised fine-tuning, and contrastive preference optimization to train the large language model (LLM) based MT model. By using Minimum Bayesian risk (MBR) decoding to select the final translation from multiple hypotheses for NMT and LLM-based MT models, our submission receives competitive results in the final evaluation.

📄 PDF Abstract BibTeX arXiv:2409.14800

Code (0)

등록된 구현이 없습니다.

Tasks

Ensemble LearningLanguage ModelingLanguage ModellingLarge Language ModelMachine TranslationNMTTranslation

Similar Papers 제목 키워드 기반

Single-Queue Decoding for Neural Machine Translation

2017-07-06 · Raphael Shu, Hideki Nakayama

Neural machine translation models rely on the beam search algorithm for decoding. In practice, we found that the quality of hypotheses in the search space is negatively affected owing to the fixed beam size. To mitigate …

Machine TranslationTranslation

An Empirical Study of Translation Hypothesis Ensembling with Large Language Models

2023-10-17 · António Farinhas, José G. C. de Souza, André F. T. Martins

Large language models (LLMs) are becoming a one-fits-many solution, but they sometimes hallucinate or produce unreliable output. In this paper, we investigate how hypothesis ensembling can improve the quality of the gene…

DiversityMachine TranslationRerankingTranslation

Improving Beam Search by Removing Monotonic Constraint for Neural Machine Translation

2018-07-01 · ACL 2018 7 · Raphael Shu, Hideki Nakayama

To achieve high translation performance, neural machine translation models usually rely on the beam search algorithm for decoding sentences. The beam search finds good candidate translations by considering multiple hypot…

Language ModelingLanguage ModellingMachine TranslationTranslation

TSMind: Alibaba and Soochow University's Submission to the WMT22 Translation Suggestion Task

2022-11-16 · Xin Ge, Ke Wang, Jiayi Wang, Nini Xiao 외

This paper describes the joint submission of Alibaba and Soochow University, TSMind, to the WMT 2022 Shared Task on Translation Suggestion (TS). We participate in the English-German and English-Chinese tasks. Basically, …

Data AugmentationLanguage ModelingLanguage ModellingTranslation

Exploring Recombination for Efficient Decoding of Neural Machine Translation

2018-08-25 · EMNLP 2018 10 · Zhisong Zhang, Rui Wang, Masao Utiyama, Eiichiro Sumita 외

In Neural Machine Translation (NMT), the decoder can capture the features of the entire prediction history with neural connections and representations. This means that partial hypotheses with different prefixes will be r…

DecoderMachine TranslationNMTTranslation