Proceedings of the 2nd Workshop on Computational Approaches to Discourse 2021
DOI: 10.18653/v1/2021.codi-main.14
|View full text |Cite
|
Sign up to set email alerts
|

Capturing document context inside sentence-level neural machine translation models with self-training

Abstract: Neural machine translation (NMT) has arguably achieved human level parity when trained and evaluated at the sentence-level. Document-level neural machine translation has received less attention and lags behind its sentence-level counterpart. The majority of the proposed document-level approaches investigate ways of conditioning the model on several source or target sentences to capture document context. These approaches require training a specialized NMT model from scratch on parallel document-level corpora. W… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3

Citation Types

0
3
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
3
1
1

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(3 citation statements)
references
References 27 publications
0
3
0
Order By: Relevance
“…For instance, some improvements obtained with context-aware models, as measured by standard translation metrics, may be attributed to context-driven regularisation acting as a noise generator, particularly with small-scale data (Kim et al, 2019;Li et al, 2020). Nonetheless, several studies have established that context information can indeed be effectively modelled to tackle discursive phenomena in NMT beyond the sentence level (Liu and Zhang, 2020;Rikters and Nakazawa, 2021;Xu et al, 2021;Mansimov et al, 2021;Gete et al, 2023).…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…For instance, some improvements obtained with context-aware models, as measured by standard translation metrics, may be attributed to context-driven regularisation acting as a noise generator, particularly with small-scale data (Kim et al, 2019;Li et al, 2020). Nonetheless, several studies have established that context information can indeed be effectively modelled to tackle discursive phenomena in NMT beyond the sentence level (Liu and Zhang, 2020;Rikters and Nakazawa, 2021;Xu et al, 2021;Mansimov et al, 2021;Gete et al, 2023).…”
Section: Related Workmentioning
confidence: 99%
“…Alternatively, sentence-level translations can be refined via reinforcement learning (Xiong et al, 2019;Mansimov et al, 2021) or monolingual repair to post-edit contextual errors in the target language (Voita et al, 2019a). More recently, the use of pretrained language models has been explored for the task, using them to encode the context (Wu et al, 2022) or to initialize NMT models (Huang et al, 2023).…”
Section: Related Workmentioning
confidence: 99%
“…In this section we discuss a few additional less related papers which were not included in our survey in Section A.1. Our discourse paraphraser is closely related to work on contextual machine translation, where source/target context is used to improve sentence-level machine translation (House, 2006;Jean et al, 2017;Wang et al, 2017;Tiedemann and Scherrer, 2017;Kuang et al, 2018;Agrawal et al, 2018;Miculicich et al, 2018;Jean et al, 2019;Voita et al, 2019a;Yin et al, 2021;Mansimov et al, 2021). Prior work has shown that context helps with anaphora resolution (Voita et al, 2018), deixis, ellipsis, and lexical cohesion (Voita et al, 2019b).…”
Section: A2 Other Related Workmentioning
confidence: 99%