paper-with-me

Papers

Non-Autoregressive Document-Level Machine Translation

2023-05-22 · Guangsheng Bao, Zhiyang Teng, Hao Zhou, Jianhao Yan, Yue Zhang

Non-autoregressive translation (NAT) models achieve comparable performance and superior speed compared to auto-regressive translation (AT) models in the context of sentence-level machine translation (MT). However, their abilities are unexplored in document-level MT, hindering their usage in real scenarios. In this paper, we conduct a comprehensive examination of typical NAT models in the context of document-level MT and further propose a simple but effective design of sentence alignment between source and target. Experiments show that NAT models achieve high acceleration on documents, and sentence alignment significantly enhances their performance. However, current NAT models still have a significant performance gap compared to their AT counterparts. Further investigation reveals that NAT models suffer more from the multi-modality and misalignment issues in the context of document-level MT, and current NAT models struggle with exploiting document context and handling discourse phenomena. We delve into these challenges and provide our code at \url{https://github.com/baoguangsheng/nat-on-doc}.

📄 PDF Abstract BibTeX arXiv:2305.12878

Code (1)

baoguangsheng/nat-on-doc 공식 구현 pytorch

Tasks

Document Level Machine TranslationMachine TranslationSentenceText GenerationTranslation

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Better Document-Level Machine Translation with Bayes' Rule

2019-10-01 · TACL 2020 1 · Lei Yu, Laurent Sartran, Wojciech Stokowiec, Wang Ling 외

We show that Bayes' rule provides an effective mechanism for creating document translation models that can be learned from only parallel sentences and monolingual documents---a compelling benefit as parallel documents ar…

Document Level Machine TranslationDocument TranslationLanguage ModelingLanguage Modelling+3

Tencent AI Lab Machine Translation Systems for WMT20 Chat Translation Task

2020-11-01 · WMT (EMNLP) 2020 11 · Longyue Wang, Zhaopeng Tu, Xing Wang, Li Ding 외

This paper describes the Tencent AI Lab’s submission of the WMT 2020 shared task on chat translation in English-German. Our neural machine translation (NMT) systems are built on sentence-level, document-level, non-autore…

General KnowledgeMachine TranslationNMTSentence+1

Document Level Hierarchical Transformer

2021-12-01 · ALTA 2021 12 · Najam Zaidi, Trevor Cohn, Gholamreza Haffari

Generating long and coherent text is an important and challenging task encompassing many application areas such as summarization, document level machine translation and story generation. Despite the success in modeling i…

Document Level Machine TranslationImitation LearningMachine TranslationSentence+2

Using Perturbed Length-aware Positional Encoding for Non-autoregressive Neural Machine Translation

2021-07-29 · Yui Oka, Katsuhito Sudoh, Satoshi Nakamura

Non-autoregressive neural machine translation (NAT) usually employs sequence-level knowledge distillation using autoregressive neural machine translation (AT) as its teacher model. However, a NAT model often outputs shor…

Knowledge DistillationMachine TranslationTranslation

Document-Level Neural Machine Translation Using BERT as Context Encoder

2020-12-01 · Asian Chapter of the Association for Computational Linguistics 2020 · Zhiyu Guo, Minh Le Nguyen

Large-scale pre-trained representations such as BERT have been widely used in many natural language understanding tasks. The methods of incorporating BERT into document-level machine translation are still being explored.…

DecoderDocument Level Machine TranslationMachine TranslationNatural Language Understanding+2