Multi-Source Neural Machine Translation with Missing Data

Nishimura, Yoshiyuki; Sudoh, Katsuhito; Neubig, Graham; Nakamura, Satoshi

doi:10.18653/v1/w18-2711

Cited by 43 publications

(21 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some works target learning a universal representation for all languages either by leveraging semantic sharing between mapped word embeddings (Gu et al, 2018) or by using character n-gram embeddings (Wang et al, 2019) optimizing subword sharing. More related with data augmentation, Nishimura et al (2018) fill in missing data with a multi-source setting to boost multilingual translation.…”

Section: Related Workmentioning

confidence: 99%

Generalized Data Augmentation for Low-Resource Translation

Xia

Kong

Anastasopoulos

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Self Cite

View full text Add to dashboard Cite

Translation to or from low-resource languages (LRLs) poses challenges for machine translation in terms of both adequacy and fluency. Data augmentation utilizing large amounts of monolingual data is regarded as an effective way to alleviate these problems. In this paper, we propose a general framework for data augmentation in low-resource machine translation that not only uses target-side monolingual data, but also pivots through a related highresource language (HRL). Specifically, we experiment with a two-step pivoting method to convert high-resource data to the LRL, making use of available resources to better approximate the true data distribution of the LRL. First, we inject LRL words into HRL sentences through an induced bilingual dictionary. Second, we further edit these modified sentences using a modified unsupervised machine translation framework. Extensive experiments on four low-resource datasets show that under extreme low-resource settings, our data augmentation techniques improve translation quality by up to 1.5 to 8 BLEU points compared to supervised back-translation baselines.

show abstract

Section: Related Workmentioning

confidence: 99%

Generalized Data Augmentation for Low-Resource Translation

Xia

Kong

Anastasopoulos

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Self Cite

View full text Add to dashboard Cite

show abstract

“…In all of their experiments, the multi-source methods significantly surpass the single-source baseline. Nishimura et al (2018) extend the former approach for situations when of the source languages is missing, so that the translation system does not overly rely on a single source language like some of the models presented in this work.…”

Section: Related Workmentioning

confidence: 99%

Input Combination Strategies for Multi-Source Transformer Decoder

Libovický¹,

Helcl²,

Mareċek³

2018

Proceedings of the Third Conference on Machine Translation: Research Papers

View full text Add to dashboard Cite

In multi-source sequence-to-sequence tasks, the attention mechanism can be modeled in several ways. This topic has been thoroughly studied on recurrent architectures. In this paper, we extend the previous work to the encoder-decoder attention in the Transformer architecture. We propose four different input combination strategies for the encoderdecoder attention: serial, parallel, flat, and hierarchical. We evaluate our methods on tasks of multimodal translation and translation with multiple source languages. The experiments show that the models are able to use multiple sources and improve over single source baselines.

show abstract

“…Domain adaptation: Some contributions examined regularization methods for adaptation and "extreme adaptation" to individual speakers (Michel and Neubig, 2018) Data augmentation: A number of the contributed papers examined ways to augment data for more efficient training. These include methods for considering multiple back translations , iterative back translation (Hoang et al, 2018b), bidirectional multilingual training (Niu et al, 2018), and document level adaptation (Kothur et al, 2018) Inadequate resources: Several contributions involved settings in which resources were insufficient, such as investigating the impact of noise , missing data in multi-source settings (Nishimura et al, 2018) and one-shot learning (Pham et al, 2018).…”

Section: Summary Of Research Contributionsmentioning

confidence: 99%

Findings of the Second Workshop on Neural Machine Translation and Generation

Birch¹,

Finch

Luong

et al. 2018

Proceedings of the 2nd Workshop on Neural Machine Translation and Generation

Self Cite

View full text Add to dashboard Cite

This document describes the findings of the Second Workshop on Neural Machine Translation and Generation, held in concert with the annual conference of the Association for Computational Linguistics (ACL 2018). First, we summarize the research trends of papers presented in the proceedings, and note that there is particular interest in linguistic structure, domain adaptation, data augmentation, handling inadequate resources, and analysis of models. Second, we describe the results of the workshop's shared task on efficient neural machine translation (NMT), where participants were tasked with creating NMT systems that are both accurate and efficient.

show abstract

Multi-Source Neural Machine Translation with Missing Data

Cited by 43 publications

References 16 publications

Generalized Data Augmentation for Low-Resource Translation

Generalized Data Augmentation for Low-Resource Translation

Input Combination Strategies for Multi-Source Transformer Decoder

Findings of the Second Workshop on Neural Machine Translation and Generation

Contact Info

Product

Resources

About